© 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. 28403
    Prev
    Next
    INDEX
    Explanations

    references to color palettes or schemes

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

    color palette and design

    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
    دانشنامهٔ
    -0.46
     is
    -0.44
    suck
    -0.44
     Howie
    -0.39
     Grow
    -0.39
     Great
    -0.38
    run
    -0.38
     in
    -0.37
     John
    -0.37
    Grow
    -0.37
    POSITIVE LOGITS
     palette
    1.31
     Palette
    1.26
    palette
    1.23
    Palette
    1.15
     palettes
    1.13
    QPalette
    0.88
     palet
    0.82
     paleta
    0.81
     palate
    0.80
     pallet
    0.70
    Activations Density 0.003%

    No Known Activations