© 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. 21-GEMMASCOPE-RES-16K
    11. 10429
    Prev
    Next
    INDEX
    Explanations

    references to posthumous honors and awards related to Michael Jackson

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     propOrder
    -0.48
    énario
    -0.45
    ñora
    -0.40
     ModelRenderer
    -0.39
    unzel
    -0.38
    󠁧
    -0.35
     mxArray
    -0.35
    Demografia
    -0.35
    ‍♀️
    -0.35
     fatta
    -0.35
    POSITIVE LOGITS
     deceased
    0.94
     death
    0.88
     died
    0.86
     posthum
    0.84
    deceased
    0.81
     Deceased
    0.79
     décédé
    0.79
     deaths
    0.77
     fallecido
    0.76
     død
    0.73
    Activations Density 0.494%

    No Known Activations