© 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. 37-GEMMASCOPE-RES-16K
    11. 701
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PageModule
    -0.37
    NavController
    -0.34
     perda
    -0.31
    (__('
    -0.30
    對象
    -0.29
     DataTypes
    -0.29
    控制器
    -0.29
    stdint
    -0.29
    BagLayout
    -0.29
    LikeLike
    -0.28
    POSITIVE LOGITS
     secret
    1.00
     secrets
    0.94
    secret
    0.93
    Secret
    0.88
     Secret
    0.87
     credentials
    0.85
     Environment
    0.83
     environment
    0.82
    SECRET
    0.82
     env
    0.79
    Activations Density 0.442%

    No Known Activations