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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 120854
    Prev
    Next
    INDEX
    Explanations

    terms related to gameplay mechanics or actions in a gaming context

    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
    IndentedString
    -0.60
    出版年
    -0.57
    tvguidetime
    -0.54
    NameInMap
    -0.52
     transférez
    -0.50
    CopyWith
    -0.49
    windowFixed
    -0.46
    ukone
    -0.45
     coughing
    -0.44
    ussis
    -0.43
    POSITIVE LOGITS
    esModule
    0.41
     IBOutlet
    0.39
     الرياضيه
    0.37
     Hongrie
    0.35
     castillo
    0.32
    postsleuth
    0.32
     linguri
    0.32
     للمعارف
    0.32
     Egyp
    0.31
     obt
    0.31
    Activations Density 0.003%

    No Known Activations