© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2627
    Prev
    Next
    INDEX
    Explanations

    references to honors and recognitions in the context of biographical details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    titles and honors related to British nobility and military ranks.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mentions of formal honors, titles, and ranks—especially military or chivalric awards and official appointments/promotions.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    British honorific titles and military ranks, especially when followed by "of the Order of the British Empire" or baronetcy designations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UpInside
    -0.62
    AndEndTag
    -0.55
    iastes
    -0.54
    RegressionTest
    -0.52
    principalTable
    -0.50
     mix
    -0.49
     verse
    -0.48
     initComponents
    -0.48
     insuffisamment
    -0.48
    はじめに
    -0.47
    POSITIVE LOGITS
     gelar
    0.44
     conferred
    0.42
    glGen
    0.42
     honorary
    0.42
     derajat
    0.41
     corporativa
    0.41
     tytu
    0.40
     bestowed
    0.40
     rumahnya
    0.40
     getStatus
    0.37
    Activations Density 0.150%

    No Known Activations