© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 119680
    Prev
    Next
    INDEX
    Explanations

    the declaration of a main function in programming code

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

    programming main

    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
     former
    -0.30
    idikan
    -0.30
     pengh
    -0.30
    没有了
    -0.29
     producido
    -0.28
    には
    -0.28
     насеље
    -0.28
    rouvez
    -0.28
     producer
    -0.28
     jus
    -0.28
    POSITIVE LOGITS
     Main
    1.61
    Main
    1.37
     MAIN
    0.98
     AssemblyTitle
    0.90
     CURIAM
    0.88
     initComponents
    0.85
    setVerticalGroup
    0.85
    IsPostBack
    0.84
    MAIN
    0.84
    getMain
    0.81
    Activations Density 0.001%

    No Known Activations