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. 80251
    Prev
    Next
    INDEX
    Explanations

    statements or claims regarding events or opinions

    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
    ंदीखरीदारी
    -0.71
     ProtoMessage
    -0.62
    лтемелер
    -0.61
     esternos
    -0.60
    IntoConstraints
    -0.59
     Италијани
    -0.59
    ByVersion
    -0.58
     fileList
    -0.58
    Життєпис
    -0.58
    хьтан
    -0.57
    POSITIVE LOGITS
    ScopeManager
    0.36
     speaks
    0.33
     наме
    0.32
     Nutz
    0.31
     spoken
    0.31
     ex
    0.31
     details
    0.30
    wiada
    0.30
     speaking
    0.30
     asking
    0.30
    Activations Density 0.018%

    No Known Activations