© 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. 11-GEMMASCOPE-RES-16K
    11. 13074
    Prev
    Next
    INDEX
    Explanations

    name mentions and familial relationships

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Caitlin
    -0.52
     Caitlin
    -0.50
    Jakub
    -0.48
    Chiara
    -0.48
    Meghan
    -0.47
    Kristina
    -0.47
    tamientos
    -0.46
     Kristina
    -0.46
    Alexandra
    -0.46
     Jakub
    -0.46
    POSITIVE LOGITS
     Orville
    0.65
    RegistryLite
    0.55
     Willard
    0.52
     Elmer
    0.52
     Cecil
    0.51
     Maurice
    0.50
     Mabel
    0.50
     Clarence
    0.49
     Doreen
    0.49
     Horace
    0.47
    Activations Density 0.543%

    No Known Activations