© 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. 31-GEMMASCOPE-RES-16K
    11. 3128
    Prev
    Next
    INDEX
    Explanations

    quantities and counts related to events, employees, and species

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

    numbers and quantities associated with large groups or collections of people, items, or organizational units.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    AsUp
    -0.68
    Personendaten
    -0.67
     queſta
    -0.65
    homonymie
    -0.62
    oredCriteria
    -0.62
     propOrder
    -0.61
     tartalomajánló
    -0.60
    estacks
    -0.59
    inheritDoc
    -0.59
    sizeCache
    -0.57
    POSITIVE LOGITS
     total
    0.96
     totalt
    0.85
     altogether
    0.82
    total
    0.80
     overall
    0.77
     répar
    0.74
     insgesamt
    0.73
     divided
    0.71
     totaal
    0.70
     Altogether
    0.70
    Activations Density 0.636%

    No Known Activations