© 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. 17-GEMMASCOPE-RES-16K
    11. 13018
    Prev
    Next
    INDEX
    Explanations

    sentiments expressing superiority and arrogance towards specific groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagLayout
    -0.49
     للتو
    -0.47
    lask
    -0.45
     Gün
    -0.41
     آور
    -0.41
     sát
    -0.40
    Corr
    -0.40
     zprá
    -0.39
    GeneratedMessage
    -0.39
     esponja
    -0.39
    POSITIVE LOGITS
     superiority
    1.04
    superior
    0.93
     arrog
    0.87
     superior
    0.80
     haughty
    0.75
     arro
    0.74
     condescending
    0.73
    lepiej
    0.72
     pompous
    0.72
     arrogant
    0.71
    Activations Density 0.254%

    No Known Activations