© 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. 15-GEMMASCOPE-RES-16K
    11. 6327
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to power dynamics and allegiance in social or political contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     الرياضيه
    -0.42
     laid
    -0.38
     consigo
    -0.34
    Зноскі
    -0.33
     thiệu
    -0.32
     mal
    -0.31
     <>",
    -0.31
     Berührung
    -0.30
    vikling
    -0.30
     supply
    -0.29
    POSITIVE LOGITS
     subserv
    0.73
     obedience
    0.71
     submissive
    0.71
     obedient
    0.68
     Obedience
    0.68
    obedience
    0.65
     obed
    0.64
    featureID
    0.63
     subordination
    0.63
     obey
    0.61
    Activations Density 0.856%

    No Known Activations