© 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. 108256
    Prev
    Next
    INDEX
    Explanations

    references to various resources and sources of information

    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
     sources
    -0.95
     source
    -0.90
     Source
    -0.86
     Sources
    -0.86
    sources
    -0.82
     sumber
    -0.80
     fuentes
    -0.77
    Sources
    -0.77
     SOURCE
    -0.76
     SOURCES
    -0.75
    POSITIVE LOGITS
    LookAnd
    0.77
     CreateTagHelper
    0.70
    EDEFAULT
    0.60
     nonUne
    0.59
     <=",
    0.56
    IUrlHelper
    0.56
    invokeLater
    0.52
    endregion
    0.52
     indisponible
    0.52
    تقاوى
    0.51
    Activations Density 0.010%

    No Known Activations