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. 20-GEMMASCOPE-RES-131K
    6. 122686
    Prev
    Next
    INDEX
    Explanations

    terms related to political party obligations and candidate nominations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.59
    ThroughAttribute
    -0.50
    SuspendLayout
    -0.50
    expandindo
    -0.48
     ffilmiau
    -0.48
     ब्रेकडाउन
    -0.47
     cherchés
    -0.47
    awtextra
    -0.47
     NSCoder
    -0.46
    VideoCapture
    -0.46
    POSITIVE LOGITS
     widers
    0.35
     reman
    0.34
     remor
    0.34
    chest
    0.33
     متفاوت
    0.33
     Neale
    0.33
     referrerpolicy
    0.33
     termica
    0.32
     REM
    0.32
    walla
    0.31
    Activations Density 0.081%

    No Known Activations