© 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 - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 6224
    Prev
    Next
    INDEX
    Explanations

    terms associated with locations, particularly in Wales, and specific cultural references

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    TargetException
    -0.54
     crude
    -0.45
     Norges
    -0.45
     Venez
    -0.39
    affaire
    -0.39
     allergies
    -0.39
    osg
    -0.39
    ceptre
    -0.38
     Frig
    -0.38
    Lähteet
    -0.37
    POSITIVE LOGITS
     Welsh
    0.88
    Welsh
    0.88
     rhestr
    0.88
     Wales
    0.77
    Wales
    0.72
     Cymru
    0.69
     wales
    0.63
    Cardiff
    0.63
    ffilm
    0.62
     Swansea
    0.59
    Activations Density 1.117%

    No Known Activations