© 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. 4729
    Prev
    Next
    INDEX
    Explanations

    snippets of programming code related to player actions and game entity management

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

    singleton pattern implementations and lazy initialization of service instances.

    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
    webElement
    -0.50
    oneof
    -0.40
     '{@
    -0.39
     Tratt
    -0.38
     desee
    -0.36
    SqlParameter
    -0.36
     SERIES
    -0.35
    WebElement
    -0.35
    QPushButton
    -0.35
    roughts
    -0.35
    POSITIVE LOGITS
     useAppContext
    0.73
     singleton
    0.69
     global
    0.64
    全局
    0.63
     Singleton
    0.60
     globales
    0.60
     Global
    0.59
     getInstance
    0.59
    webElementXpaths
    0.58
    global
    0.57
    Activations Density 0.508%

    No Known Activations