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. 92837
    Prev
    Next
    INDEX
    Explanations

    code elements related to creating or defining components and functions in programming, particularly in a JavaScript or React context

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

    create or creation operations

    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
     zijne
    -0.58
     mijne
    -0.51
     relojes
    -0.50
     esquí
    -0.47
     Polsek
    -0.47
     teléfonos
    -0.47
     piernas
    -0.46
    aimana
    -0.46
     felicidad
    -0.46
    rouvez
    -0.46
    POSITIVE LOGITS
    makeText
    0.62
    createCell
    0.61
     createContext
    0.60
    createTextNode
    0.58
     Creation
    0.56
    createStatement
    0.55
    IntoConstraints
    0.55
     onCreateView
    0.54
    Creation
    0.52
    createUser
    0.52
    Activations Density 0.017%

    No Known Activations