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. 2639
    Prev
    Next
    INDEX
    Explanations

    references to specific countries, governmental entities, and organizations related to issues or actions of national significance

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

    countries, states, and cities

    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
     arşivlendi
    -0.60
    verifyException
    -0.54
     resourceCulture
    -0.50
    ViewFeatures
    -0.49
    MLLoader
    -0.48
    posedge
    -0.47
    contentLoaded
    -0.44
     Италијани
    -0.44
    曖昧さ回避
    -0.41
    tispiece
    -0.41
    POSITIVE LOGITS
    DockStyle
    0.42
     traduction
    0.37
    ofType
    0.35
     HFILL
    0.35
     allAfrica
    0.35
     uska
    0.35
     vuelto
    0.34
    phosa
    0.34
     routine
    0.34
    
    0.34
    Activations Density 0.104%

    No Known Activations