© 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. 105511
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to problem-solving and working through issues

    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
    retudo
    -0.49
     pingente
    -0.48
     confidence
    -0.48
     kapsul
    -0.47
     digitais
    -0.46
    Попис
    -0.46
     bouteille
    -0.45
     adesivos
    -0.44
     brinquedos
    -0.44
     retrovisor
    -0.43
    POSITIVE LOGITS
    working
    0.75
     Worked
    0.69
    Working
    0.68
    worked
    0.67
    work
    0.66
    Worked
    0.66
     working
    0.63
     worked
    0.63
    Work
    0.63
     Work
    0.61
    Activations Density 0.013%

    No Known Activations