© 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. 22-GEMMASCOPE-RES-16K
    11. 11832
    Prev
    Next
    INDEX
    Explanations

    issues related to physical wear and compatibility in materials or components

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     industry
    -0.35
     Perusahaan
    -0.33
     corporativa
    -0.33
    IMER
    -0.32
    тябрь
    -0.32
     Vorsitzender
    -0.32
    Prospect
    -0.31
     aufgebaut
    -0.31
     Vorsitzende
    -0.31
    Industry
    -0.31
    POSITIVE LOGITS
     ujednoznacz
    0.69
     defaultstate
    0.69
     '\\;'
    0.66
    IsContent
    0.62
     שוליים
    0.60
    
    0.60
     ब्रेकडाउन
    0.57
    reportWebVitals
    0.57
     ویکی‌پدی
    0.57
    SequentialGroup
    0.54
    Activations Density 0.566%

    No Known Activations