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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1808
    Prev
    Next
    INDEX
    Explanations

    accolades and awards related to sports players and coaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idhi
    -0.53
     fun
    -0.50
    راق
    -0.49
    Fun
    -0.48
    stanti
    -0.47
    getReal
    -0.47
    бурга
    -0.47
     its
    -0.46
     Fun
    -0.44
    منابع
    -0.44
    POSITIVE LOGITS
    writeFieldEnd
    0.89
     lenker
    0.83
    rungsseite
    0.78
    IntoConstraints
    0.77
     allAfrica
    0.69
     onCreateView
    0.66
    QMetaType
    0.66
    NOPQRST
    0.65
     actionMode
    0.65
    +#+
    0.64
    Activations Density 0.039%

    No Known Activations