© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 118090
    Prev
    Next
    INDEX
    Explanations

    structural elements and syntax patterns in programming code

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

    code and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -1.14
    CloseOperation
    -0.99
    invokeLater
    -0.96
    AsUp
    -0.91
     Италијани
    -0.85
    bootstrapcdn
    -0.84
     ModelExpression
    -0.81
    LookAnd
    -0.80
    ConverterFactory
    -0.78
     informée
    -0.78
    POSITIVE LOGITS
    Safety
    0.33
    Rec
    0.31
     tavo
    0.31
    <0xAD>
    0.30
    Entry
    0.30
     Rec
    0.30
     Humphries
    0.30
    cac
    0.30
     Su
    0.29
    Mem
    0.29
    Activations Density 0.084%

    No Known Activations