Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7316
    Prev
    Next
    INDEX
    Explanations

    specific references to social dynamics, particularly involving race and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    iſen
    -0.72
     stockbild
    -0.71
     ſind
    -0.69
     beſte
    -0.69
     $_"
    -0.69
     $_(
    -0.69
    ſchaft
    -0.68
     beſti
    -0.68
    rungsseite
    -0.68
    出版年
    -0.67
    POSITIVE LOGITS
     arşivlendi
    0.41
     καλ
    0.27
    require
    0.25
     imp
    0.24
    HasColumnName
    0.24
    原标题
    0.24
     kunne
    0.23
     ligt
    0.22
     involve
    0.22
    երի
    0.22
    Activations Density 0.223%

    No Known Activations