© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104814
    Prev
    Next
    INDEX
    Explanations

    conditional statements and logical operations in code

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     receptor
    -0.36
     fusca
    -0.33
     lat
    -0.32
     Imperial
    -0.32
     عز
    -0.31
     Kela
    -0.31
     Receptor
    -0.30
     hospital
    -0.30
    ℃
    -0.29
     Box
    -0.29
    POSITIVE LOGITS
     Reisedaten
    0.61
    EDEFAULT
    0.57
     ujednoznacz
    0.57
    béco
    0.56
     onCancelled
    0.54
    MigrationBuilder
    0.54
    ANDUM
    0.54
    disposing
    0.52
    InitVars
    0.51
    ChildScrollView
    0.50
    Activations Density 0.046%

    No Known Activations