© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 537
    Prev
    Next
    INDEX
    Explanations

    terms and references related to Node.js and npm (Node Package Manager)

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

    code related to Node.js and npm (Node package manager) commands

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

    Node.js JavaScript

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     GenerationType
    -0.60
    zeba
    -0.57
     torchvision
    -0.52
    Netto
    -0.52
    ariously
    -0.52
     Bromley
    -0.49
    stdarg
    -0.49
    ⎧
    -0.49
    承
    -0.49
    sustain
    -0.49
    POSITIVE LOGITS
     forKey
    0.66
    parsedMessage
    0.57
    EndGlobalSection
    0.55
    invokeLater
    0.54
    JS
    0.53
    IndentedString
    0.52
     Oden
    0.52
    findpost
    0.50
    ocrine
    0.48
    LookAnd
    0.47
    Activations Density 0.030%

    No Known Activations