Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12962
    Prev
    Next
    INDEX
    Explanations

    various forms of baked goods and desserts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    cake and baking

    np_acts-logits-general · gemini-2.0-flash

    baking and cakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.67
    Rhestr
    -0.57
    Gravel
    -0.57
    Jeep
    -0.55
     Mantis
    -0.54
     Wrangler
    -0.52
     Gravel
    -0.52
    getResultList
    -0.52
     Charlton
    -0.51
    POOL
    -0.51
    POSITIVE LOGITS
     cake
    2.02
     cakes
    1.83
     Cake
    1.80
     bake
    1.65
     Cakes
    1.64
    cake
    1.64
     baking
    1.64
    Cake
    1.62
     CAKE
    1.61
     baker
    1.54
    Activations Density 0.122%

    No Known Activations