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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5756
    Prev
    Next
    INDEX
    Explanations

    programming language keywords related to imports and dependencies

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

    code imports and statements

    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
    oredCriteria
    -0.50
    AccessorTable
    -0.49
    цездатний
    -0.46
    IsMutable
    -0.41
    WebMethod
    -0.41
     Commencez
    -0.40
    Empereur
    -0.40
    hasMore
    -0.40
     everywhere
    -0.40
     saites
    -0.39
    POSITIVE LOGITS
    WithIOException
    0.51
    awtextra
    0.50
    IContainer
    0.46
    setVerticalGroup
    0.45
    richTextPanel
    0.45
     informée
    0.44
     defaultstate
    0.44
    ]")]
    0.43
    出版年
    0.42
    __*/
    0.41
    Activations Density 0.002%

    No Known Activations