© 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. 2-GEMMASCOPE-RES-16K
    11. 611
    Prev
    Next
    INDEX
    Explanations

    the opening of a document or section

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     miniaturka
    -0.77
     Chwiliwch
    -0.73
    хьтан
    -0.70
     męska
    -0.68
     Geſch
    -0.68
     kasarigan
    -0.67
    Referințe
    -0.66
     ویکی‌پدی
    -0.66
     tartalomajánló
    -0.65
    pecabe
    -0.65
    POSITIVE LOGITS
     she
    0.58
     
    0.56
     her
    0.56
     he
    0.53
     him
    0.46
    He
    0.46
    She
    0.46
     his
    0.44
     them
    0.43
     carro
    0.39
    Activations Density 0.176%

    No Known Activations