© 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. 101116
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to statistical analysis and performance metrics in models

    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
     autorytatywna
    -0.59
     Reverso
    -0.53
    openzeppelin
    -0.52
     informée
    -0.50
    Története
    -0.49
    XmlAccessorType
    -0.49
     AssemblyCompany
    -0.48
     Exactos
    -0.48
    gnore
    -0.48
     overs
    -0.48
    POSITIVE LOGITS
     performance
    0.43
    findpost
    0.40
     förb
    0.38
    发表于
    0.38
     improvement
    0.37
     Dichtung
    0.37
     énergé
    0.36
    Enllaços
    0.36
     zufried
    0.34
     výkon
    0.34
    Activations Density 0.049%

    No Known Activations