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

    Neuronpedia

    APICircuit 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. 3-GEMMASCOPE-RES-16K
    6. 10936
    Prev
    Next
    INDEX
    Explanations

    terms related to baking and the process of cooking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mendoza
    -0.74
     board
    -0.62
    дивиду
    -0.60
     Strath
    -0.59
    StructEnd
    -0.58
    rum
    -0.58
     Ruff
    -0.57
    Kot
    -0.56
    ment
    -0.56
     Pand
    -0.55
    POSITIVE LOGITS
     BAKER
    1.24
    Baker
    1.23
     Baker
    1.22
     Bake
    1.04
    Bake
    1.04
     bake
    1.00
     Bakers
    0.99
    Baked
    0.97
    bake
    0.94
     baker
    0.92
    Activations Density 0.134%

    No Known Activations