© 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. 3-GEMMASCOPE-RES-16K
    11. 11564
    Prev
    Next
    INDEX
    Explanations

    terms related to jets and their applications in geometry or algebra

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     تضيفلها
    -0.56
    بوابة
    -0.45
     للاسماء
    -0.45
    AuthProvider
    -0.43
    wnątrz
    -0.43
     visse
    -0.43
    AnimationsModule
    -0.43
     culturel
    -0.42
    onomian
    -0.42
     internetowa
    -0.41
    POSITIVE LOGITS
     Jer
    0.99
    jet
    0.96
    Jer
    0.93
     jet
    0.91
    Jet
    0.90
     Jet
    0.90
    JET
    0.90
     Jes
    0.89
     j
    0.88
     jLabel
    0.88
    Activations Density 1.124%

    No Known Activations