© 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. 105413
    Prev
    Next
    INDEX
    Explanations

    constructs related to programming or coding syntax

    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
    TypedDataSet
    -0.82
    WaitGroup
    -0.71
    ConstraintMaker
    -0.69
     مرئيه
    -0.66
     AssemblyCulture
    -0.65
    ValueGeneration
    -0.65
    MLLoader
    -0.61
    
    -0.61
     ProtoMessage
    -0.61
    يكب
    -0.59
    POSITIVE LOGITS
     poveznice
    0.35
    Externé
    0.35
    Примечания
    0.33
    Kjelder
    0.31
    TargetApi
    0.29
     planned
    0.28
     Friedens
    0.28
     sayap
    0.28
     <<<<<<<<<<<<<<
    0.26
     zwing
    0.26
    Activations Density 0.584%

    No Known Activations