© 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. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 111247
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "ua."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ua
    -2.39
    UA
    -1.70
    úa
    -1.25
    uaa
    -1.22
     ua
    -1.16
    uas
    -1.13
     UA
    -0.97
    uae
    -0.87
    uak
    -0.85
    oua
    -0.81
    POSITIVE LOGITS
    endphp
    0.45
    OrBuilder
    0.43
    endpush
    0.40
     Vikipedi
    0.34
    endsection
    0.34
    듈
    0.33
    IntoConstraints
    0.31
    Korn
    0.30
    pay
    0.30
    тивов
    0.30
    Activations Density 0.001%

    No Known Activations