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. 365
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and quotation marks used in dialogue or denoting speech

    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
    Tikang
    -0.57
    tagHelperRunner
    -0.57
    principalTable
    -0.50
    msgid
    -0.50
    ]</
    -0.50
    ;"></
    -0.49
    maxcdn
    -0.49
     onAnimation
    -0.49
    kannt
    -0.48
    LabelTagHelper
    -0.47
    POSITIVE LOGITS
     referenties
    0.84
     _('
    0.73
    //
    0.72
     Jody
    0.70
    ',['
    0.69
    ]-'
    0.69
    Portail
    0.68
    <th>
    0.66
     VIAF
    0.65
    SharedCtor
    0.65
    Activations Density 0.003%

    No Known Activations