© 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. 108040
    Prev
    Next
    INDEX
    Explanations

    mathematical set operations and expressions

    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
    -0.45
    ThemeOverlay
    -0.43
    bigoplus
    -0.41
     كومونز
    -0.39
    bigcup
    -0.38
     felicità
    -0.38
    ientí
    -0.37
     AssemblyProduct
    -0.37
    TagMode
    -0.36
     Bagian
    -0.36
    POSITIVE LOGITS
    guiente
    0.50
     ménage
    0.49
    Totale
    0.43
    XmlEnum
    0.42
     resolution
    0.41
    wakili
    0.41
    DeleteBehavior
    0.41
     Lyt
    0.40
     Resolution
    0.39
     Sol
    0.39
    Activations Density 0.067%

    No Known Activations