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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7239
    Prev
    Next
    INDEX
    Explanations

    JavaScript code that interacts with the DOM

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the `document` object followed by a period and method/property names in JavaScript code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ụy
    -0.25
    yaç
    -0.25
    =?";
    -0.25
    人気
    -0.24
    ṯ
    -0.24
     dommage
    -0.23
     racked
    -0.23
    Viki
    -0.23
     PANEL
    -0.23
     lui
    -0.23
    POSITIVE LOGITS
    MigrationBuilder
    0.67
     cherchés
    0.65
    getElementById
    0.64
     houſe
    0.64
    Personendaten
    0.63
     greateſt
    0.61
     ſche
    0.61
     ſind
    0.60
    balleur
    0.60
    SequentialGroup
    0.59
    Activations Density 0.048%

    No Known Activations