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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1516
    Prev
    Next
    INDEX
    Explanations

    mentions of voting and elections, particularly in relation to democracy and the majority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Klein
    -0.51
     Maitland
    -0.49
     Schmid
    -0.48
     McMillan
    -0.48
     Howell
    -0.48
     Stevens
    -0.47
     and
    -0.47
     Linder
    -0.45
     complicated
    -0.45
    aderas
    -0.45
    POSITIVE LOGITS
     vote
    1.20
     Vote
    1.09
     VOTE
    1.02
    Vote
    0.99
     voting
    0.94
     Voting
    0.91
     voted
    0.90
    Voting
    0.89
    vote
    0.89
    VOTE
    0.88
    Activations Density 0.321%

    No Known Activations