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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15316
    Prev
    Next
    INDEX
    Explanations

    Java import statements related to various libraries and packages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.89
     ModelExpression
    -0.78
     estekak
    -0.71
    matchCondition
    -0.70
    ########.
    -0.69
    RTSC
    -0.67
     Wikimedijinoj
    -0.67
    __":
    
    -0.67
     Normdatei
    -0.65
    UnitTesting
    -0.64
    POSITIVE LOGITS
    ://
    0.39
    AlterField
    0.37
    fasterxml
    0.31
     boxes
    0.31
     мощности
    0.30
    /
    0.29
    ,
    0.29
     reg
    0.29
     lever
    0.28
     straws
    0.28
    Activations Density 0.048%

    No Known Activations