© 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-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 6441
    Prev
    Next
    INDEX
    Explanations

    descriptions of luxurious amenities and scenic views

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.69
     otomatig
    -0.65
    তথ্যসূত্র
    -0.62
    ngdoc
    -0.62
    matchCondition
    -0.55
     Italijanski
    -0.55
    ScopeManager
    -0.54
     deuil
    -0.54
     voici
    -0.53
    Legături
    -0.52
    POSITIVE LOGITS
     view
    2.22
     views
    1.95
    view
    1.84
     View
    1.77
     Views
    1.70
     VIEW
    1.66
    View
    1.66
    VIEW
    1.55
    views
    1.52
    Views
    1.46
    Activations Density 0.212%

    No Known Activations