© 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. 33-GEMMASCOPE-RES-16K
    11. 14663
    Prev
    Next
    INDEX
    Explanations

    key relational terms and phrases that indicate importance or ownership in a narrative

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Related
    -0.40
    某
    -0.40
    又一次
    -0.39
    Salve
    -0.38
    上一
    -0.36
    >({
    -0.36
    之一
    -0.36
     sice
    -0.35
    Related
    -0.35
    一度
    -0.35
    POSITIVE LOGITS
     rest
    2.67
     remainder
    2.50
     remaining
    2.22
     resten
    2.19
     Remaining
    2.08
    remaining
    1.91
    Remaining
    1.91
     restante
    1.90
    remainder
    1.87
     restantes
    1.85
    Activations Density 0.761%

    No Known Activations