© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 14289
    Prev
    Next
    INDEX
    Explanations

    selectors used in code, particularly in programming or scripting contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.56
    <h2>
    -0.56
     Stras
    -0.56
    <i>
    -0.54
    Autoritní
    -0.53
    Trey
    -0.53
    bagai
    -0.52
     QtGui
    -0.52
     tys
    -0.52
    างเกง
    -0.52
    POSITIVE LOGITS
    selector
    1.95
    Selector
    1.84
     Selector
    1.80
     selector
    1.74
     selectors
    1.33
    selectors
    1.20
    SEL
    1.02
     Sel
    0.94
    principalTable
    0.90
    Sel
    0.90
    Activations Density 0.109%

    No Known Activations