© 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. 27-GEMMASCOPE-RES-16K
    11. 12746
    Prev
    Next
    INDEX
    Explanations

    significant shifts in narrative or context within a text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Bibliograf
    -0.40
    versy
    -0.40
    MLLoader
    -0.38
     arac
    -0.37
     baptism
    -0.36
    geer
    -0.35
     geçen
    -0.34
    dsi
    -0.33
     Behör
    -0.33
    lecular
    -0.33
    POSITIVE LOGITS
    这时候
    1.18
    这时
    1.16
    这个时候
    1.12
    此時
    1.00
     allora
    0.99
     entonces
    0.99
     then
    0.94
     wtedy
    0.93
    その時
    0.92
     THEN
    0.87
    Activations Density 0.294%

    No Known Activations