© 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-2-2B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 2357
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of uncovering or disclosing secrets or truths

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     
    -0.78
    ftagPool
    -0.76
     U
    -0.68
      
    -0.66
    verband
    -0.64
     colspan
    -0.64
    o
    -0.63
     I
    -0.60
     D
    -0.60
    läng
    -0.59
    POSITIVE LOGITS
     Reveal
    1.65
     Reveals
    1.43
    Reveal
    1.42
     reveal
    1.41
     Reve
    1.37
     reveals
    1.36
    reveal
    1.34
     disclosure
    1.31
     Revealed
    1.30
     disclose
    1.29
    Activations Density 0.083%

    No Known Activations