© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 3076
    Prev
    Next
    INDEX
    Explanations

    the closing braces and semicolons often used in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.67
    PYX
    -0.53
    okovic
    -0.52
    TintMode
    -0.50
     ModelExpression
    -0.47
    abyrinth
    -0.47
    대로
    -0.46
     aDecoder
    -0.45
    луй
    -0.45
     barrels
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.77
     muualla
    0.71
     שוליים
    0.68
     kasarigan
    0.63
     insuffisamment
    0.61
    DotNetBar
    0.61
    UnsafeEnabled
    0.60
    ContentAsync
    0.60
    abestanden
    0.59
    InjectAttribute
    0.58
    Activations Density 0.036%

    No Known Activations