© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102624
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "sc" likely associated with programming or scripting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    GIVEREF
    -0.61
    LookAnd
    -0.57
    AntiForgeryToken
    -0.56
    NamedQueries
    -0.52
    principalColumn
    -0.52
    MessageOf
    -0.51
     ModelExpression
    -0.47
    ReusableCell
    -0.47
    SpringRunner
    -0.46
    IsContent
    -0.45
    POSITIVE LOGITS
    scriptcase
    1.27
     sc
    0.80
    sc
    0.75
    nmgp
    0.69
    adaptiveStyles
    0.67
     Sc
    0.64
    Sc
    0.64
    SC
    0.54
     SC
    0.54
    tinyos
    0.50
    Activations Density 0.000%

    No Known Activations