© 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. 0-GEMMASCOPE-RES-16K
    11. 3964
    Prev
    Next
    INDEX
    Explanations

    temporal measurements and durations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     <=",
    -0.50
     חיצוניים
    -0.50
    topper
    -0.48
    raff
    -0.48
    SequentialGroup
    -0.48
    expansion
    -0.47
     Winaray
    -0.47
     softens
    -0.47
    tops
    -0.46
    trends
    -0.45
    POSITIVE LOGITS
     years
    1.27
     weeks
    1.19
     months
    1.17
     yrs
    1.11
     days
    1.01
    years
    0.94
    weeks
    0.92
    months
    0.91
    yrs
    0.87
     años
    0.87
    Activations Density 0.337%

    No Known Activations