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. 19-GEMMASCOPE-RES-16K
    6. 2205
    Prev
    Next
    INDEX
    Explanations

    URLs and parameters associated with web requests

    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
     שוליים
    -0.76
     invokingState
    -0.73
     للمعارف
    -0.71
    RenderAtEndOf
    -0.70
    ViewImports
    -0.69
    tagHelperRunner
    -0.68
    migrationBuilder
    -0.67
    /");
    -0.64
    ?')
    -0.63
     MessageBoxIcon
    -0.63
    POSITIVE LOGITS
    &
    1.58
    \&
    1.16
    }&
    1.08
    +"&
    1.05
     '&
    1.02
     "&
    0.99
    &&
    0.96
    '&
    0.95
    .&
    0.92
    )&
    0.92
    Activations Density 0.451%

    No Known Activations