© 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. 418
    Prev
    Next
    INDEX
    Explanations

    terms relating to conditions being classified as severe

    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
     EconPapers
    -0.81
     مشين
    -0.63
     envy
    -0.56
    TagMode
    -0.52
    Espèce
    -0.52
     snip
    -0.50
     CreateTagHelper
    -0.50
    DockStyle
    -0.50
     Scholarships
    -0.49
     ویکی‌پدیا
    -0.49
    POSITIVE LOGITS
     instances
    0.90
     scenes
    0.75
     characters
    0.68
     occasions
    0.66
     những
    0.60
     Fällen
    0.59
     incidents
    0.59
    instances
    0.59
     victims
    0.58
     cases
    0.56
    Activations Density 0.171%

    No Known Activations