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. 21-GEMMASCOPE-RES-16K
    6. 12520
    Prev
    Next
    INDEX
    Explanations

    references to a specific term or variable related to "Sarcoma"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     numberWith
    -0.71
    [](
    -0.58
    antaine
    -0.58
    حياتها
    -0.57
    исленность
    -0.56
     Verbre
    -0.56
    حياته
    -0.55
     actionMode
    -0.53
    getBytes
    -0.52
     كومونز
    -0.52
    POSITIVE LOGITS
    Sar
    0.88
     Sar
    0.82
     sar
    0.81
    fillType
    0.60
     onOptions
    0.58
     sari
    0.56
     Sarac
    0.56
     للاسماء
    0.56
     Saras
    0.55
    sar
    0.53
    Activations Density 0.096%

    No Known Activations