© 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. 3-GEMMASCOPE-RES-16K
    11. 8491
    Prev
    Next
    INDEX
    Explanations

    mentions of different republics, particularly focusing on the term "Republic"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     author
    -0.36
     architecture
    -0.35
     אב
    -0.35
    ౖ
    -0.34
     Haig
    -0.34
     spis
    -0.34
     hébergement
    -0.34
    zwungen
    -0.33
    ريكي
    -0.32
     housing
    -0.32
    POSITIVE LOGITS
     trap
    0.79
     Republic
    0.75
    Republic
    0.72
     '{@
    0.71
    UrlResolution
    0.71
    Radar
    0.71
    trap
    0.70
     Trap
    0.69
    Clik
    0.69
     Prom
    0.68
    Activations Density 0.175%

    No Known Activations