© 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. 41-GEMMASCOPE-RES-16K
    11. 7735
    Prev
    Next
    INDEX
    Explanations

    phrases related to election outcomes and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     économ
    -0.43
    MigrationBuilder
    -0.42
    NewUrlParser
    -0.42
    .*")]
    -0.41
     économies
    -0.40
    MLLoader
    -0.40
    angelog
    -0.40
    новништво
    -0.40
    ControllerAdvice
    -0.39
     noDo
    -0.39
    POSITIVE LOGITS
     polling
    1.03
     electoral
    0.96
     voter
    0.96
     voters
    0.89
     Electoral
    0.88
     voting
    0.83
     election
    0.83
     Voter
    0.82
     ballot
    0.81
     INEC
    0.80
    Activations Density 0.158%

    No Known Activations