© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11286
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and code structures in technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming language syntax and code structure patterns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.66
     Taktlose
    -0.57
    Diweddarwch
    -0.56
    PreExecute
    -0.56
    VersionUID
    -0.55
    FailureListener
    -0.54
    Microkernel
    -0.53
    jsonwebtoken
    -0.53
     onPostExecute
    -0.52
    
    -0.52
    POSITIVE LOGITS
     Independent
    0.38
     sitten
    0.35
    Independent
    0.35
    >--}}
    0.34
     Security
    0.34
     bijzonder
    0.32
     Society
    0.31
     Customs
    0.30
     Agg
    0.30
    Nothing
    0.29
    Activations Density 0.814%

    No Known Activations