© 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. 107878
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to dental health and substances involved in oral care

    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
    脚注の使い方
    -0.49
    PreExecute
    -0.49
    RectangleBorder
    -0.47
     BoxDecoration
    -0.46
    <tfoot>
    -0.45
    mbalikan
    -0.44
    AutoScaleMode
    -0.44
    vrigt
    -0.42
     BoxFit
    -0.41
    itteet
    -0.41
    POSITIVE LOGITS
     jspb
    0.54
     swallows
    0.40
    stdc
    0.40
    inform
    0.38
    usser
    0.38
     Vamos
    0.38
    NUMX
    0.37
    defn
    0.36
     humble
    0.36
    WriteTagHelper
    0.36
    Activations Density 0.166%

    No Known Activations