Get the latest tech news
DeepMind’s Gemma Scope peers under the hood of large language models
Google DeepMind has released Gemma Scope, a series of sparse autoencoders (SAEs) that help interpret Gemma 2 models.
Gemma Scope builds on top of JumpReLU sparse autoencoders (SAEs), a deep learning architecture that DeepMind recently proposed. “Further research has the potential to help the field build more robust systems, develop better safeguards against model hallucinations, and protect against risks from autonomous AI agents like deception or manipulation.” As LLMs continue to advance and become more widely adopted in enterprise applications, AI labs are racing to provide tools that can help them better understand and control the behavior of these models.
Or read this on Venture Beat
