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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 2252
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↠
    -0.60
    andır
    -0.59
    principalColumn
    -0.54
    endphp
    -0.53
    nameof
    -0.53
    百科
    -0.50
    saraba
    -0.50
    وأضاف
    -0.49
     revanche
    -0.48
    ectoria
    -0.48
    POSITIVE LOGITS
    ScopeManager
    0.63
    RUnlock
    0.62
    RenderAtEndOf
    0.61
     ExecuteAsync
    0.61
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.58
    aság
    0.57
    vician
    0.57
    <?
    0.56
    <
    0.55
    bewerken
    0.55
    Activations Density 0.109%

    No Known Activations