© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42705
    Prev
    Next
    INDEX
    Explanations

    terms related to scoring and evaluation metrics in data analysis

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    scoring evaluating majority votes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    Negative Logits
     كومونز
    -0.47
    Hentet
    -0.46
    asticity
    -0.46
    libft
    -0.46
    脚注の使い方
    -0.45
    guez
    -0.43
    єра
    -0.42
     Normdatei
    -0.41
    
    -0.41
     deschis
    -0.40
    POSITIVE LOGITS
    WebElementEntity
    0.44
     scoring
    0.41
    endphp
    0.38
     votes
    0.36
     Scores
    0.35
     Scoring
    0.34
     rained
    0.34
     counter
    0.34
    paramref
    0.33
    WaitGroup
    0.33
    Activations Density 0.097%

    No Known Activations