© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105769
    Prev
    Next
    INDEX
    Explanations

    symbols and numeric values, often related to statistical or categorical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.73
    IntoConstraints
    -0.71
    RenderAtEndOf
    -0.63
    DockStyle
    -0.62
    ьаж
    -0.60
    MockMvc
    -0.59
    MigrationBuilder
    -0.57
    yntaxException
    -0.56
    ConstraintMaker
    -0.55
    tonode
    -0.54
    POSITIVE LOGITS
    ckså
    0.34
    Cap
    0.34
    ectady
    0.33
    Red
    0.32
     éditoriale
    0.31
    zitter
    0.31
    endregion
    0.29
    ்த்த
    0.29
    UpdatedBy
    0.28
     âmes
    0.28
    Activations Density 0.034%

    No Known Activations