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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 91976
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to app management and user account interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     zijne
    -0.42
    Życiorys
    -0.39
     funções
    -0.39
    ilarang
    -0.38
     lunares
    -0.38
    uncias
    -0.37
    pNext
    -0.36
     määrä
    -0.36
    awtextra
    -0.36
     todella
    -0.36
    POSITIVE LOGITS
     للمعارف
    0.50
    niająca
    0.48
    InitVars
    0.47
    principalColumn
    0.46
    Viitteet
    0.46
    drag
    0.46
     WB
    0.46
     مرئيه
    0.44
     reb
    0.44
     sup
    0.43
    Activations Density 0.022%

    No Known Activations