© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2962
    Prev
    Next
    INDEX
    Explanations

    terms related to voting and elections

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

    voting

    np_acts-logits-general · gemini-2.0-flash

    vote casting or confidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.87
    Hozzáférés
    -0.73
     EconPapers
    -0.71
     كومونز
    -0.68
     Wib
    -0.65
    Tembelea
    -0.65
    دانشنامهٔ
    -0.63
    theless
    -0.62
    iNdEx
    -0.60
    Awkward
    -0.60
    POSITIVE LOGITS
    SqlClient
    0.79
     votes
    0.75
     vote
    0.74
     Vote
    0.72
    votes
    0.69
     VOTE
    0.67
    Votes
    0.63
     voto
    0.63
    futbolista
    0.62
    vote
    0.62
    Activations Density 0.186%

    No Known Activations