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. 468
    Prev
    Next
    INDEX
    Explanations

    references to medical or clinical guidelines and studies

    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
    \{\\
    -0.88
     initComponents
    -0.66
    ंदीखरीदारी
    -0.62
    ThroughAttribute
    -0.60
    Демографія
    -0.58
     المعيارى
    -0.58
    جمعیت
    -0.56
     propOrder
    -0.56
     opérateur
    -0.50
     promessa
    -0.47
    POSITIVE LOGITS
     ſche
    0.73
     themſelves
    0.72
     itſelf
    0.71
     standards
    0.66
     ſtand
    0.65
    ſelves
    0.64
     purpoſe
    0.63
     standardi
    0.63
     ſp
    0.63
     standard
    0.62
    Activations Density 0.016%

    No Known Activations