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. 979
    Prev
    Next
    INDEX
    Explanations

    structured data fields and their attributes

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

    scored, created, Hero, Academia, height, label, log, pathname

    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
    VersionUID
    -0.45
     disponibilités
    -0.37
     contrário
    -0.37
    CGRectMake
    -0.36
    Referencies
    -0.35
     TAMBÉM
    -0.33
    AnimationsModule
    -0.33
    yntaxException
    -0.32
    libft
    -0.31
    retudo
    -0.30
    POSITIVE LOGITS
     resourceCulture
    0.73
     Administrativna
    0.63
     Савезне
    0.63
    parsedMessage
    0.60
     oprot
    0.59
    uxxxx
    0.59
     BRI
    0.57
    WireFormatLite
    0.56
    Cyfarwyddwr
    0.54
    請繼續往下閱讀
    0.54
    Activations Density 0.177%

    No Known Activations