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. 85344
    Prev
    Next
    INDEX
    Explanations

    references to Canadian provinces and territories

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

    Canadian provinces and citizens

    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
     uș
    -0.54
    ViewFeatures
    -0.53
    Hochspringen
    -0.51
     Etats
    -0.47
    Manbalar
    -0.46
    maß
    -0.45
    protoimpl
    -0.45
     creș
    -0.43
    liferay
    -0.43
     Еще
    -0.42
    POSITIVE LOGITS
     Canada
    1.12
     Canadian
    1.11
    Canada
    1.06
     Canadians
    1.03
    カナダ
    1.02
    Canadian
    1.01
    加拿大
    1.01
     CANADA
    0.99
    TAWA
    0.98
     Toronto
    0.96
    Activations Density 0.197%

    No Known Activations