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. 73360
    Prev
    Next
    INDEX
    Explanations

    SQL commands and database-related keywords

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

    for homepage, appellant, user

    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
    InjectAttribute
    -0.50
    Rüyada
    -0.48
    __":
    
    -0.46
    __':
    
    -0.43
     Wikiseite
    -0.40
     wikipagina
    -0.40
    SuspendLayout
    -0.37
     fieltro
    -0.37
     λα
    -0.36
     Einwilligung
    -0.36
    POSITIVE LOGITS
    Xna
    0.53
     ProtoMessage
    0.47
    CPtr
    0.44
    IBOutlet
    0.43
     tartalomajánló
    0.42
    LITERAL
    0.42
    libft
    0.40
    MethodManager
    0.40
     typelib
    0.40
    RectangleBorder
    0.40
    Activations Density 0.048%

    No Known Activations