© 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. 36-GEMMASCOPE-RES-16K
    11. 5016
    Prev
    Next
    INDEX
    Explanations

    names of individuals, likely focusing on people involved in legal or professional contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     flechas
    -0.55
     Hitam
    -0.54
     econômica
    -0.54
     gavetas
    -0.53
     tatuagens
    -0.52
     Putih
    -0.52
    parken
    -0.51
     financeira
    -0.50
     ángeles
    -0.50
     braço
    -0.49
    POSITIVE LOGITS
    mann
    0.65
    ke
    0.53
    MANN
    0.46
    man
    0.46
     mann
    0.46
    entra
    0.44
    berg
    0.43
    hardt
    0.43
     lein
    0.42
     gau
    0.42
    Activations Density 0.388%

    No Known Activations