© 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. 10-GEMMASCOPE-RES-16K
    11. 2683
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "private."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Reſ
    -0.73
    ſelf
    -0.72
     itſelf
    -0.71
     Anſ
    -0.69
     kasarigan
    -0.67
     ſever
    -0.66
     InputDecoration
    -0.65
    ſelves
    -0.64
    MessageTagHelper
    -0.63
     tranſ
    -0.62
    POSITIVE LOGITS
    private
    2.81
     private
    2.27
     Private
    1.98
    Private
    1.93
     PRIVATE
    1.86
    PRIVATE
    1.74
     privaten
    1.58
     privately
    1.55
     privada
    1.45
     privado
    1.44
    Activations Density 0.035%

    No Known Activations