© 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. 107995
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to scientific and technical concepts

    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
     vPvB
    -0.54
    jsxFileName
    -0.54
    HomeAsUpEnabled
    -0.53
    /*
    -0.52
     BorderSide
    -0.52
    reportWebVitals
    -0.50
    VersionUID
    -0.49
    ffine
    -0.49
     BoxFit
    -0.49
    enderror
    -0.48
    POSITIVE LOGITS
    Sade
    0.36
     cal
    0.35
    ThroughAttribute
    0.35
    CAL
    0.34
    Domin
    0.33
    InternalFrame
    0.32
    Vertical
    0.32
    cal
    0.32
    %">
    0.32
     Busse
    0.32
    Activations Density 0.050%

    No Known Activations