© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 461
    Prev
    Next
    INDEX
    Explanations

    statements related to electoral outcomes and announcements

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

    discussions and statements about voter fraud allegations and election integrity concerns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.59
    MigrationBuilder
    -0.56
     unknownFields
    -0.51
    Formazione
    -0.49
    uncur
    -0.48
    rhosis
    -0.47
    MessageState
    -0.46
     defStyleAttr
    -0.45
    endphp
    -0.45
     محفوظة
    -0.45
    POSITIVE LOGITS
     voter
    1.34
     Election
    1.30
     election
    1.27
     electoral
    1.26
     voting
    1.19
     voters
    1.17
     Voter
    1.16
     Electoral
    1.15
     Voting
    1.10
    Election
    1.09
    Activations Density 0.349%

    No Known Activations