Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 Tom Lieberum author Senthooran Rajamanoharan author Arthur Conmy author Lewis Smith author Nicolas Sonnerat author Vikrant Varma author Janos Kramar author Anca Dragan author Rohin Shah author Neel Nanda author 2024-11 text Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP Yonatan Belinkov editor Najoung Kim editor Jaap Jumelet editor Hosein Mohebbi editor Aaron Mueller editor Hanjie Chen editor Association for Computational Linguistics Miami, Florida, US conference publication lieberum-etal-2024-gemma 10.18653/v1/2024.blackboxnlp-1.19 https://aclanthology.org/2024.blackboxnlp-1.19/ 2024-11 278 300