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. 18
    Prev
    Next
    INDEX
    Explanations

    SQL command keywords

    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
     يتيمه
    -0.68
    
    -0.66
    bootstrapcdn
    -0.59
    ChildScrollView
    -0.58
     propOrder
    -0.57
    󠁴
    -0.57
    ffrey
    -0.56
    canActivate
    -0.55
    godic
    -0.55
     initComponents
    -0.54
    POSITIVE LOGITS
    createCell
    0.59
    "))
    
    0.53
    $")
    0.50
    ẵn
    0.48
    存于互联网档案馆
    0.47
    gång
    0.47
    Parcelize
    0.46
    新品
    0.46
    tesse
    0.45
    $',
    0.44
    Activations Density 0.000%

    No Known Activations