© 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. 7-GEMMASCOPE-RES-16K
    11. 12285
    Prev
    Next
    INDEX
    Explanations

    elements related to educational structure and curriculum

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    出版年
    -0.71
     الرياضيه
    -0.50
    writeFieldEnd
    -0.48
     univerz
    -0.47
    :✨
    -0.47
    aderas
    -0.45
    BeginContext
    -0.44
    érieure
    -0.43
     يتيمه
    -0.42
    complexContent
    -0.40
    POSITIVE LOGITS
     Schülerinnen
    0.47
    calaureate
    0.43
    โรง
    0.43
    ronpa
    0.43
    MathML
    0.43
    校長
    0.42
    STEM
    0.41
    Mr
    0.41
    PyExc
    0.41
     auß
    0.41
    Activations Density 0.664%

    No Known Activations