Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29576
    Prev
    Next
    INDEX
    Explanations

    programming-related terms or concepts, particularly those associated with application context and initialization in software development

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

    startup runner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.57
     يتيمه
    -0.52
     ligiloj
    -0.50
    henswürdigkeiten
    -0.48
    endregion
    -0.46
    mobileqq
    -0.45
    ftagPool
    -0.43
     createState
    -0.42
     StatefulWidget
    -0.41
     invokingState
    -0.40
    POSITIVE LOGITS
    Runner
    1.34
     Runner
    0.90
    Runners
    0.88
     runner
    0.85
     runners
    0.80
    runner
    0.80
    runners
    0.72
     Runners
    0.71
    RUN
    0.54
     documentaire
    0.54
    Activations Density 0.000%

    No Known Activations