© 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. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 13380
    Prev
    Next
    INDEX
    Explanations

    instances of challenging or precarious situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.62
    AntiForgeryToken
    -0.54
    AnchorTagHelper
    -0.51
    Personendaten
    -0.50
     Wikimedijinoj
    -0.47
     AssemblyTitle
    -0.45
    AddTagHelper
    -0.45
     ModelRenderer
    -0.44
     MenuView
    -0.42
    EndGlobalSection
    -0.41
    POSITIVE LOGITS
     trap
    0.87
     rut
    0.86
     predicament
    0.85
     bind
    0.84
     pickle
    0.75
     mire
    0.74
     binds
    0.73
     mess
    0.71
     situation
    0.69
     limbo
    0.69
    Activations Density 0.396%

    No Known Activations