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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 45444
    Prev
    Next
    INDEX
    Explanations

    the term "other" in various contexts

    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
    loc
    -0.37
    vedra
    -0.36
    Geografi
    -0.35
    stays
    -0.33
    TableId
    -0.32
    location
    -0.31
     Celui
    -0.31
     lobby
    -0.30
    ply
    -0.30
    combined
    -0.30
    POSITIVE LOGITS
    Примечания
    4.56
    Зноскі
    1.71
    Примітки
    1.50
    Ссылки
    1.48
    әрмәләр
    1.42
    Источники
    1.36
    İstinadlar
    1.33
    Jegyzetek
    1.27
    Przypisy
    1.25
    Lähteet
    1.23
    Activations Density 0.001%

    No Known Activations