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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Post
    5. 12-GEMMASCOPE-RES-1M
    6. 97
    Prev
    Next
    INDEX
    Explanations

    phrases related to injury and fatalities in a military context

    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_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    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
    srand
    -0.59
     surla
    -0.58
    StoryboardSegue
    -0.58
    最快更新
    -0.57
    GORITH
    -0.57
    endphp
    -0.57
    eclamp
    -0.56
     minOccurs
    -0.54
     ويكيميديا
    -0.54
    havn
    -0.52
    POSITIVE LOGITS
     cardiaque
    0.53
    cotta
    0.51
     exceptionnelle
    0.51
     dentaire
    0.51
     istri
    0.50
    jatel
    0.50
     finnas
    0.49
     ansatte
    0.49
    dition
    0.49
     patrol
    0.49
    Activations Density 0.003%

    No Known Activations