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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5866
    Prev
    Next
    INDEX
    Explanations

    references to voter fraud and election integrity issues

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

    discussions about voting processes, voter registration, and voter fraud.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    OCCURRED
    -0.55
    tagHelperRunner
    -0.50
     Infórmanos
    -0.48
    cèse
    -0.47
    MessageState
    -0.47
    ISupport
    -0.46
     Olímpicos
    -0.46
     actionMode
    -0.43
     صوتيه
    -0.43
     Мексичка
    -0.43
    POSITIVE LOGITS
     voter
    0.71
     ballots
    0.69
     voting
    0.66
     voters
    0.64
     ballot
    0.63
     Voter
    0.62
     polling
    0.59
     electoral
    0.57
     Voting
    0.57
    voter
    0.53
    Activations Density 0.174%

    No Known Activations