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

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9682
    Prev
    Next
    INDEX
    Explanations

    data types and their declarations in programming contexts

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

    Java Integer variables

    np_acts-logits-general · gemini-2.0-flash

    Integer, Long, Float variable types

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     betweenstory
    -0.38
     Afford
    -0.37
     JADX
    -0.37
    Derbyniad
    -0.37
    Karriere
    -0.36
    mée
    -0.34
    ::~
    -0.32
     Costs
    -0.31
     Confessions
    -0.31
     bure
    -0.31
    POSITIVE LOGITS
    Integer
    1.14
     Integer
    1.11
    NSNumber
    0.73
    getInteger
    0.71
     Boolean
    0.69
    Boolean
    0.65
    interopRequire
    0.60
     Float
    0.58
    IndentedString
    0.57
     ModelExpression
    0.56
    Activations Density 0.067%

    No Known Activations