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. 31-GEMMASCOPE-RES-131K
    6. 91010
    Prev
    Next
    INDEX
    Explanations

    terms related to programming structures and methods in code

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

    board configurations and composition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yarnpkg
    -0.40
    principalColumn
    -0.39
     '{@
    -0.37
     disponibilités
    -0.36
    awarkan
    -0.35
    nloa
    -0.35
    NavLink
    -0.34
     ارش
    -0.33
    URLEncoder
    -0.33
    Questão
    -0.32
    POSITIVE LOGITS
     consisting
    0.67
     consists
    0.63
     consisted
    0.60
     size
    0.59
     terdiri
    0.50
     length
    0.50
     odkazy
    0.49
     tamanho
    0.48
     consist
    0.47
     members
    0.47
    Activations Density 0.098%

    No Known Activations