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-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1197
    Prev
    Next
    INDEX
    Explanations

    references to political campaigns and their elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    campaigns and elections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gradova
    -0.36
    GEBURTSDATUM
    -0.36
    <!--[
    -0.36
    meyi
    -0.35
     obdob
    -0.34
     externo
    -0.33
     opgenomen
    -0.33
     quizás
    -0.33
     précédente
    -0.33
     måske
    -0.32
    POSITIVE LOGITS
     campaign
    0.79
    Campaign
    0.79
     campaigning
    0.76
     Campaign
    0.73
     CAMPAIGN
    0.73
    paign
    0.70
    campaign
    0.70
     campa
    0.65
     campaigns
    0.63
     campaigned
    0.63
    Activations Density 0.034%

    No Known Activations