© 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. 36-GEMMASCOPE-RES-16K
    11. 4868
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to statistical estimators and calculations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ویکی‌پدی
    -0.62
    httphttps
    -0.47
     thiệu
    -0.46
    __(/*!
    -0.45
     utafitiHapana
    -0.43
    yntaxException
    -0.42
     архивлан
    -0.41
     ويكيپيديا
    -0.41
    OCCURRED
    -0.41
    satellite
    -0.40
    POSITIVE LOGITS
     sum
    3.45
    sum
    3.03
     Sum
    3.00
    Sum
    2.94
     SUM
    2.80
    SUM
    2.64
     sums
    2.50
     summation
    2.44
     Summe
    2.36
     summing
    2.30
    Activations Density 1.256%

    No Known Activations