© 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. 15720
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court rulings and verdicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     supposedly
    -0.46
     conocer
    -0.38
     supuestamente
    -0.37
     billions
    -0.34
     conoci
    -0.34
    乓
    -0.34
     reportedly
    -0.33
     talk
    -0.33
     banal
    -0.33
    豪
    -0.33
    POSITIVE LOGITS
    RegressionTest
    0.60
    setVerticalGroup
    0.59
    луй
    0.57
     concorda
    0.55
     وتسجيلات
    0.54
     ModelExpression
    0.52
    mybatisplus
    0.52
    IsContent
    0.52
    Hauptartikel
    0.50
    HtmlAttribute
    0.49
    Activations Density 0.502%

    No Known Activations