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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4520
    Prev
    Next
    INDEX
    Explanations

    references to cultural or national identities, particularly related to Asian and European countries

    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
     kasarigan
    -0.88
     Roskov
    -0.86
    igneurs
    -0.81
    IsContent
    -0.67
    :✨
    -0.67
    protoimpl
    -0.67
     للاسماء
    -0.66
     blisters
    -0.65
     loch
    -0.65
    elemField
    -0.64
    POSITIVE LOGITS
     American
    1.05
     Canadian
    0.99
     Indian
    0.97
    American
    0.95
     British
    0.91
    Canadian
    0.89
     Mexican
    0.87
     Australian
    0.87
     European
    0.83
     French
    0.82
    Activations Density 0.200%

    No Known Activations