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. 0-GEMMASCOPE-RES-16K
    6. 8011
    Prev
    Next
    INDEX
    Explanations

    references to feet and related body parts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IGraphics
    -0.59
    KOK
    -0.51
     وتسجيلات
    -0.48
     Gor
    -0.48
    щаются
    -0.47
    madeus
    -0.47
    govor
    -0.46
    ilite
    -0.45
     Drey
    -0.45
     Rag
    -0.45
    POSITIVE LOGITS
     foot
    2.95
     feet
    2.89
     Foot
    2.73
    foot
    2.63
    Foot
    2.60
     Feet
    2.57
     FOOT
    2.55
    feet
    2.42
    Feet
    2.33
     FEET
    2.25
    Activations Density 0.087%

    No Known Activations