© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 17604
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to nominations and the nomination process in political contexts

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

    nomination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cheminée
    -0.48
     propOrder
    -0.48
     peur
    -0.45
    ejs
    -0.45
     élect
    -0.45
     alimentaria
    -0.45
    Климаты
    -0.44
     ()=>{
    -0.44
    errHandler
    -0.43
     Slick
    -0.43
    POSITIVE LOGITS
     nomination
    2.13
     Nomination
    1.88
     nominations
    1.78
     Nominations
    1.56
    Nominations
    1.45
    omination
    1.34
     nominating
    1.13
     nomina
    1.06
     nominate
    1.03
    nomin
    0.98
    Activations Density 0.003%

    No Known Activations