© 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. 11-GEMMASCOPE-RES-16K
    11. 9267
    Prev
    Next
    INDEX
    Explanations

    references to the word "Pa" and related terms in a scientific context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     chanti
    -0.86
    SpringBootTest
    -0.85
    {{\
    -0.80
     cherchés
    -0.79
     (`
    -0.77
     McCulloch
    -0.75
    antium
    -0.74
     ['
    -0.73
     Chern
    -0.72
     Kessler
    -0.71
    POSITIVE LOGITS
     Pa
    1.30
     PA
    1.25
     pa
    1.23
    pa
    1.19
    PA
    1.15
    Pa
    1.10
     Paxton
    1.07
     Paola
    1.04
     Opa
    1.03
    PAI
    1.02
    Activations Density 0.157%

    No Known Activations