© 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. 107895
    Prev
    Next
    INDEX
    Explanations

    words related to geographic or national identifiers

    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
    ロウィン
    -0.70
    
    -0.69
    ſicht
    -0.69
    ſchaft
    -0.66
    ècie
    -0.66
    <unused52>
    -0.65
    ésultats
    -0.64
    <unused14>
    -0.64
    <unused8>
    -0.64
    <unused3>
    -0.64
    POSITIVE LOGITS
     Los
    0.30
     tengas
    0.28
    <eos>
    0.27
    la
    0.27
    ↵↵
    0.27
    ↵
    0.27
     at
    0.27
    HideFlags
    0.26
     el
    0.26
    er
    0.26
    Activations Density 0.044%

    No Known Activations