© 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. 127792
    Prev
    Next
    INDEX
    Explanations

    notations and symbols commonly used in technical or mathematical contexts

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

    code and mathematical notation

    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
    RectangleBorder
    -0.61
    AsUp
    -0.57
    DIPSETTING
    -0.52
    bootstrapcdn
    -0.46
    GenerationType
    -0.45
    IsContent
    -0.44
    leşti
    -0.44
     perbuatan
    -0.41
    #
    -0.41
     stages
    -0.40
    POSITIVE LOGITS
     intptr
    0.67
    
    0.47
    BeginContext
    0.46
    
    0.46
    endpush
    0.44
     isNameExpr
    0.44
     informée
    0.43
    RegressionTest
    0.41
     useParams
    0.40
    IRUS
    0.39
    Activations Density 0.001%

    No Known Activations