© 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. 31-GEMMASCOPE-RES-16K
    11. 3136
    Prev
    Next
    INDEX
    Explanations

    words related to nobility or titles, particularly involving 'du' and various forms of 'duke' in different contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    author names and surnames in academic citations and references.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    const
    -0.29
    (".");
    -0.28
     الب
    -0.28
    Reflection
    -0.28
     sonra
    -0.27
     aho
    -0.26
    //{
    -0.26
    get
    -0.26
     dem
    -0.26
    لينكات
    -0.26
    POSITIVE LOGITS
    Du
    0.73
     Du
    0.72
     Dup
    0.67
     Durand
    0.66
     Duchess
    0.62
     duplicates
    0.62
    rungsseite
    0.62
    Duk
    0.62
     Duf
    0.61
    Duplicates
    0.61
    Activations Density 0.173%

    No Known Activations