Grammatical "grandmother neurons" are rare in LLMs

arXiv:2609.29328 · cs.CL · Submitted 2026-09-24 · Read on arXiv

cs.CL

Submitted: 2026-09-24

Updated: 2026-09-24

Terminology

• Accuracy — 21× in this paper · explained in 1 episode
• Ablation — 14× in this paper · explained in 1 episode
• Benchmark — 11× in this paper · explained in 2 episodes
• Transformer — 11× in this paper · explained in 2 episodes
• Generalization — 8× in this paper · explained in 13 episodes
• Interpretability — 8× in this paper · explained in 15 episodes
• Neuron Separability Index — 7× in this paper
• Calibration — 6× in this paper · explained in 7 episodes
• Clustering — 5× in this paper · explained in 2 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Sparsity — 5× in this paper · explained in 4 episodes
• Empirical Methods in Natural Language Processing — 3× in this paper
• Activation Patching — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Modularity — 1× in this paper · explained in 9 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Pragmatics — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Vector Representations — 1× in this paper · explained in 2 episodes

Sources

• Identifying and Controlling Important Neurons in Neural Machine Translation
• The Llama 3 Herd of Models
• Toy Models of Superposition
• Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
• Designing and Interpreting Probes with Control Tasks
• A Systematic Assessment of Syntactic Generalization in Neural Language Models
• MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs
• The emergence of number and syntax units in LSTM language models
• A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese
• BERT Rediscovers the Classical NLP Pipeline
• What do RNN Language Models Learn about Filler-Gap Dependencies?
• Qwen3 Technical Report
• Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering