© 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. 101243
    Prev
    Next
    INDEX
    Explanations

    references to ducks or duck-related items

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.58
     Himo
    -0.47
     leeftijd
    -0.45
    fjspx
    -0.44
    fährt
    -0.44
     Jost
    -0.44
     Blackman
    -0.44
     Jir
    -0.43
    veratrol
    -0.43
    ODES
    -0.42
    POSITIVE LOGITS
     Duck
    1.19
     duck
    1.17
    Duck
    1.13
    duck
    1.03
     ducks
    1.02
     Ducks
    0.94
    ducks
    0.89
     Duckworth
    0.86
    Ducks
    0.85
     waterfowl
    0.77
    Activations Density 0.006%

    No Known Activations