© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 76009
    Prev
    Next
    INDEX
    Explanations

    references to development-related topics and terms

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

    dev, devops, devTools

    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
    uxxxx
    -0.63
     anderem
    -0.58
     financière
    -0.57
     bancaire
    -0.56
    AnchorTagHelper
    -0.54
     índice
    -0.52
     Primaria
    -0.52
     Económica
    -0.52
    ヌーピー
    -0.51
     Aiken
    -0.51
    POSITIVE LOGITS
     Dev
    1.12
    dev
    1.02
     DEV
    1.00
     dev
    1.00
    Dev
    0.99
    DEV
    0.91
     DeV
    0.75
     Devlin
    0.73
     Devon
    0.71
     DV
    0.70
    Activations Density 0.008%

    No Known Activations