© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 27337
    Prev
    Next
    INDEX
    Explanations

    references to figures and visual representations in the text

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

    fig. followed by identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    <thead>
    -0.70
    BrowserRouter
    -0.59
     ura
    -0.57
     Moreau
    -0.56
     Waterman
    -0.56
     ater
    -0.55
     Aurelius
    -0.54
    UserScript
    -0.53
    ">//
    -0.53
    tlement
    -0.53
    POSITIVE LOGITS
     Fig
    1.43
    Fig
    1.41
     Figs
    1.20
    Figs
    1.10
     fig
    1.05
    fig
    0.96
    FIG
    0.87
     figs
    0.86
     FIG
    0.85
    Рис
    0.71
    Activations Density 0.081%

    No Known Activations