© 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. 55300
    Prev
    Next
    INDEX
    Explanations

    phrases that describe details or qualities related to objects and experiences

    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
    -
    -0.54
     nemlig
    -0.50
    NonQuery
    -0.48
    _
    -0.48
    -0.48
    s
    -0.48
    isNameExpr
    -0.45
    ization
    -0.45
    ambilan
    -0.45
    ckså
    -0.45
    POSITIVE LOGITS
     ویکی‌پدیای
    0.73
     فريبيس
    0.65
    RegressionTest
    0.64
    HomeAsUpEnabled
    0.64
    adaptiveStyles
    0.62
     AssemblyVersion
    0.60
    setVerticalGroup
    0.58
    redients
    0.57
    uxxxx
    0.57
    Hochspringen
    0.57
    Activations Density 0.029%
    No Known Activations