© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 100846
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions associated with data manipulation and graphical processing

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     otomatig
    -0.81
     ExecuteAsync
    -0.79
    ftagPool
    -0.76
     فريبيس
    -0.64
     оригіналу
    -0.63
    __(/*!
    -0.63
     للمعارف
    -0.62
    fjspx
    -0.62
     contextLoads
    -0.61
     Administrativna
    -0.61
    POSITIVE LOGITS
     also
    0.56
     further
    0.50
     inoltre
    0.49
     additional
    0.43
     additionally
    0.42
     then
    0.42
    also
    0.41
     außerdem
    0.41
     accordingly
    0.40
     weitere
    0.40
    Activations Density 0.375%

    No Known Activations