© 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. 28-GEMMASCOPE-RES-16K
    11. 11874
    Prev
    Next
    INDEX
    Explanations

    keywords related to government, legal contexts, and organizations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    appearing in titles

    np_acts-logits-general · gemini-2.0-flash

    church, lin, up, treaty, duke, bola

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Highness
    -0.45
    TypeDef
    -0.45
     Excellency
    -0.44
    explo
    -0.44
    Ireland
    -0.40
    Scotland
    -0.40
    Kim
    -0.39
     Моск
    -0.39
     Majesty
    -0.39
    Pon
    -0.38
    POSITIVE LOGITS
    Rujuakan
    0.63
     considérons
    0.63
    aarrggbb
    0.62
     okuyayım
    0.58
    webElementXpaths
    0.54
    #
    0.52
    centralwidget
    0.51
    Jeografia
    0.50
     لينك
    0.47
    webtoken
    0.47
    Activations Density 1.802%

    No Known Activations