© 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. 108218
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the presence or features of items or locations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.79
     PeEnEo
    -0.65
     Савезне
    -0.59
    SourceChecksum
    -0.58
     Catawiki
    -0.56
    setVerticalGroup
    -0.55
     հղումներ
    -0.54
    ItemSelected
    -0.54
     reaſon
    -0.52
    RuleContext
    -0.52
    POSITIVE LOGITS
    ganie
    0.37
    tamiento
    0.36
    Izvori
    0.36
    PathVariable
    0.35
    Kedves
    0.34
     AssemblyCompany
    0.34
     recomendo
    0.33
    qxd
    0.33
     Ursache
    0.32
     cristianos
    0.32
    Activations Density 0.008%

    No Known Activations