© 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. 2-GEMMASCOPE-RES-16K
    11. 601
    Prev
    Next
    INDEX
    Explanations

    instances of the word "priv" and related terms associated with privacy and contracts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    acamata
    -0.45
     perdana
    -0.36
     premiers
    -0.35
     Verfahrens
    -0.33
    Somehow
    -0.32
    miljø
    -0.32
     owe
    -0.32
     Erziehung
    -0.31
     somehow
    -0.31
    曰
    -0.31
    POSITIVE LOGITS
     pri
    1.51
    Pri
    1.26
     Pri
    1.23
    pri
    1.16
     prioriti
    1.10
     prioritize
    1.00
     PRIV
    0.97
     Priority
    0.95
     Priory
    0.94
     prioritizing
    0.92
    Activations Density 0.091%

    No Known Activations