© 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. 11-GEMMASCOPE-RES-16K
    11. 3200
    Prev
    Next
    INDEX
    Explanations

    titles related to positions of authority in government and leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Teres
    -0.72
    skosten
    -0.72
    rateful
    -0.67
    Moth
    -0.65
    atorze
    -0.64
    Tf
    -0.63
     ouvertes
    -0.63
     Hurricanes
    -0.61
    patterns
    -0.60
    ︎
    -0.60
    POSITIVE LOGITS
     VICE
    0.98
     Vice
    0.96
    TabLayout
    0.92
     vice
    0.90
    PUTY
    0.87
     deputy
    0.87
    Vice
    0.82
     Dami
    0.82
     versa
    0.81
     Deputy
    0.80
    Activations Density 0.093%

    No Known Activations