© 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. 111311
    Prev
    Next
    INDEX
    Explanations

    references to clinical cases or scenarios

    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
     ivelany
    -0.60
     saites
    -0.56
    pushFollow
    -0.56
    parsedMessage
    -0.53
     surla
    -0.53
     Савезне
    -0.51
    awtextra
    -0.50
    StructEnd
    -0.49
    BufferException
    -0.49
     дописавши
    -0.49
    POSITIVE LOGITS
     survived
    0.38
     defStyleAttr
    0.36
     Auftritt
    0.36
    Sortable
    0.36
    Podemos
    0.35
    enzo
    0.35
     halbe
    0.35
     snippetHide
    0.35
     quæ
    0.35
    NOR
    0.34
    Activations Density 0.014%

    No Known Activations