AI & ML News Follow 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. https://venturebeat.com/ai/deepminds-gemma-scope-peers-under-the-hood-of-large-language-models/ venturebeat.com