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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 75495
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and software development, particularly in the context of user interface elements and event handling

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

    code, programming, research, or data context

    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
     ligera
    -0.34
     Kerja
    -0.33
     mejorado
    -0.32
     independientes
    -0.32
     ciudadana
    -0.31
     Heilige
    -0.30
     Świę
    -0.30
     juridiques
    -0.29
     helados
    -0.29
     mejora
    -0.28
    POSITIVE LOGITS
    ConstraintMaker
    0.98
     MessageBoxIcon
    0.96
    djangoproject
    0.91
    tonsoft
    0.90
     GenerationType
    0.84
    RectangleBorder
    0.83
     BoxDecoration
    0.82
     AssemblyVersion
    0.81
    WireFormatLite
    0.81
     BoxFit
    0.80
    Activations Density 0.007%

    No Known Activations