© 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. 14789
    Prev
    Next
    INDEX
    Explanations

    references to authoritarian regimes and instances of oppressive governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     škoda
    -0.35
     plegable
    -0.33
    مين
    -0.33
     preliminar
    -0.33
     ochrony
    -0.31
     mixte
    -0.31
     conoc
    -0.31
     φω
    -0.30
     Verpflichtung
    -0.30
     Allowing
    -0.30
    POSITIVE LOGITS
    IsMutable
    0.71
     totalitarian
    0.71
    DIPSETTING
    0.68
     authoritarian
    0.67
     dictator
    0.57
     Мексичка
    0.55
     repressive
    0.53
     regime
    0.53
    QMetaType
    0.52
    posedge
    0.52
    Activations Density 0.251%

    No Known Activations