© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5332
    Prev
    Next
    INDEX
    Explanations

    terms related to sanctions and bans in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anskje
    -0.52
    findpost
    -0.52
     oprot
    -0.51
     rado
    -0.49
     BoxFit
    -0.47
     RoutedEventArgs
    -0.47
    umpang
    -0.47
     שוליים
    -0.47
    Клуб
    -0.47
    jsdelivr
    -0.46
    POSITIVE LOGITS
     prohibitions
    1.11
     bans
    1.10
     banned
    1.06
     embargo
    1.05
     restrictions
    1.04
     banning
    1.03
     prohibition
    1.02
     ban
    1.01
     sanctions
    0.99
     prohibiting
    0.97
    Activations Density 0.404%

    No Known Activations