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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1643
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Republic" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rénées
    -0.63
     Hebron
    -0.63
    лектро
    -0.62
     Hurley
    -0.61
    пера
    -0.58
    ferenz
    -0.57
    Tracey
    -0.57
    drop
    -0.57
    Mikey
    -0.57
    ContentValues
    -0.56
    POSITIVE LOGITS
     Republic
    1.61
    Republic
    1.42
     republic
    1.35
     REPUBLIC
    1.31
    republic
    1.18
     republics
    1.05
     Republics
    1.01
    共和国
    0.94
     República
    0.92
     republican
    0.89
    Activations Density 0.096%

    No Known Activations