© 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. 116176
    Prev
    Next
    INDEX
    Explanations

    mentions of application configuration settings

    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
    Rüyada
    -0.59
    verwijspagina
    -0.49
    enterOuterAlt
    -0.44
    OuterAlt
    -0.42
    AntiForgeryToken
    -0.41
    MLLoader
    -0.39
    InvalidProtocol
    -0.37
    MessageTagHelper
    -0.37
    KURZBESCHREIBUNG
    -0.36
    SequentialGroup
    -0.33
    POSITIVE LOGITS
     bParam
    0.55
    Getenv
    0.52
     eşofman
    0.51
    xase
    0.50
    Werdegang
    0.48
     RISERV
    0.46
    umumkan
    0.45
    PÁG
    0.45
    alış
    0.44
     asamblea
    0.44
    Activations Density 0.008%

    No Known Activations