© 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. 111119
    Prev
    Next
    INDEX
    Explanations

    key names or identifiers related to scientific or technical subjects

    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
    -0.81
    setVerticalGroup
    -0.72
     ProtoMessage
    -0.71
    MLLoader
    -0.70
     zwiſchen
    -0.68
     imagui
    -0.67
    <unused43>
    -0.66
     AssemblyCulture
    -0.65
    <pad>
    -0.65
     Dieſe
    -0.65
    POSITIVE LOGITS
     Италијани
    0.33
     isComment
    0.28
     oğ
    0.25
     intptr
    0.24
    noin
    0.24
    ::_('
    0.24
     Савезне
    0.23
     judíos
    0.23
     informally
    0.23
    {{--
    0.21
    Activations Density 0.337%

    No Known Activations