© 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. 72714
    Prev
    Next
    INDEX
    Explanations

    key narrative elements related to character relationships and developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     employ
    -0.36
     conjunta
    -0.34
     Baillargeon
    -0.33
    の通り
    -0.33
    sidian
    -0.33
     defenders
    -0.33
     players
    -0.33
     sélection
    -0.32
     nom
    -0.32
     AssemblyCompany
    -0.31
    POSITIVE LOGITS
    MigrationBuilder
    0.68
    ########.
    0.60
    Rüyada
    0.55
    RTEX
    0.52
    TypedDataSet
    0.52
     onOptions
    0.51
     Photocase
    0.51
     autorytatywna
    0.50
     subplot
    0.50
     للاسماء
    0.50
    Activations Density 0.203%

    No Known Activations