© 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. 2-GEMMASCOPE-RES-16K
    11. 4226
    Prev
    Next
    INDEX
    Explanations

    references to the term "White," particularly in political or racial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     delle
    -0.45
     della
    -0.43
     dei
    -0.42
     NSCoder
    -0.39
     Sakai
    -0.39
     DELLE
    -0.38
     conto
    -0.34
    行
    -0.34
     privilégi
    -0.33
    Hentet
    -0.33
    POSITIVE LOGITS
     White
    0.66
     ujednoznacz
    0.65
    White
    0.62
    parsedMessage
    0.59
     paragraphs
    0.57
     Turquoise
    0.57
     Paragraph
    0.57
     initComponents
    0.57
     paragraph
    0.55
    paragraph
    0.53
    Activations Density 0.065%

    No Known Activations