© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 6647
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements in programming languages

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

    Go code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     while
    -0.40
     While
    -0.36
     try
    -0.35
    While
    -0.33
     trying
    -0.33
    _
    -0.32
     _
    -0.32
    while
    -0.31
     Bry
    -0.27
     .
    -0.27
    POSITIVE LOGITS
    rawDesc
    0.87
     propOrder
    0.85
     للاسماء
    0.82
    Personendaten
    0.82
     '\\;'
    0.81
    complexContent
    0.79
     unknownFields
    0.79
    sizeCache
    0.78
    нгред
    0.76
     disambiguazione
    0.74
    Activations Density 0.014%

    No Known Activations