© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5075
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to programming and error handling in code

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

    string concatenation and output operations in code.

    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
     ModelExpression
    -0.80
    verwijspagina
    -0.73
    parsedMessage
    -0.71
    IntoConstraints
    -0.70
     الحره
    -0.67
    ScopeManager
    -0.67
    évaluateur
    -0.66
    webElementXpaths
    -0.64
     AssemblyTitle
    -0.63
    UserScript
    -0.63
    POSITIVE LOGITS
     newline
    0.67
    换
    0.64
    br
    0.59
    newline
    0.57
     "\
    0.56
     换
    0.55
     line
    0.54
    NewLine
    0.52
     endl
    0.52
    ("\
    0.51
    Activations Density 0.815%

    No Known Activations