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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 116817
    Prev
    Next
    INDEX
    Explanations

    mentions of the NBC network and its related programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Kell
    -0.40
     Chesterfield
    -0.40
    htaccess
    -0.39
    +}\
    -0.37
    setFrom
    -0.36
     Southern
    -0.35
     southern
    -0.35
    Southern
    -0.35
    sendStatus
    -0.34
    SOUTH
    -0.34
    POSITIVE LOGITS
    IntoConstraints
    0.79
     propOrder
    0.72
     للاسماء
    0.68
     Middlesbrough
    0.62
    adaptiveStyles
    0.60
    richTextPanel
    0.60
     Ceramby
    0.60
     onResponse
    0.60
    featureID
    0.59
     NBC
    0.59
    Activations Density 0.074%

    No Known Activations