© 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. 105284
    Prev
    Next
    INDEX
    Explanations

    key terms associated with journalism and media channels

    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
     desmotivaciones
    -0.69
    //
    -0.64
     Infór
    -0.57
    gucig
    -0.57
    /*
    -0.53
     increí
    -0.50
     literario
    -0.49
     nothwendig
    -0.49
     applicazioni
    -0.49
     agradable
    -0.48
    POSITIVE LOGITS
     Shack
    0.43
     TestBed
    0.41
     RIP
    0.41
    gameserver
    0.40
     nero
    0.36
     Co
    0.35
    ruptedException
    0.34
     KAB
    0.34
     BCE
    0.34
     Rod
    0.33
    Activations Density 0.131%

    No Known Activations