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. 12-GEMMASCOPE-RES-16K
    6. 15351
    Prev
    Next
    INDEX
    Explanations

    HTTP status codes and responses indicating errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugen
    -0.49
    //}
    -0.45
    var
    -0.44
    外部リンク
    -0.42
     selv
    -0.41
    ivan
    -0.41
    atan
    -0.41
     daly
    -0.40
     assunto
    -0.40
    кон
    -0.39
    POSITIVE LOGITS
    HttpStatus
    0.94
     متعلقه
    0.81
    
    0.81
    AxisAlignment
    0.77
    AnchorStyles
    0.76
    ็จ
    0.73
    Демографія
    0.73
    ORAGE
    0.73
    ItemBackground
    0.72
     Agamemnon
    0.70
    Activations Density 0.093%

    No Known Activations