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. 33414
    Prev
    Next
    INDEX
    Explanations

    references to therapy services and community support

    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
    RTSC
    -0.54
    naturally
    -0.51
    styleType
    -0.51
     naturally
    -0.50
    rentices
    -0.49
    ViewFeatures
    -0.48
     وتسجيلات
    -0.47
     reve
    -0.47
    EDEFAULT
    -0.45
     proprement
    -0.45
    POSITIVE LOGITS
     JpaRepository
    0.45
    ArgsConstructor
    0.40
    WriteLiteral
    0.37
     psychotherapy
    0.37
    innerHeight
    0.36
    //
    0.35
     тера
    0.35
     Psychotherapy
    0.34
     sonno
    0.34
    xiety
    0.34
    Activations Density 0.024%

    No Known Activations