© 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. 24-GEMMASCOPE-RES-16K
    11. 12957
    Prev
    Next
    INDEX
    Explanations

    items or products related to banking, finance, or retail services

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

    Items for sale

    np_acts-logits-general · gemini-2.0-flash

    items, merchandise, products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     cirurgia
    -0.35
     fisuras
    -0.35
     vectoriales
    -0.35
     ragion
    -0.34
     circonstances
    -0.34
     economia
    -0.33
     leçons
    -0.33
     escena
    -0.33
    WithIOException
    -0.32
     poderes
    -0.32
    POSITIVE LOGITS
     accessories
    0.79
     tableware
    0.74
    ware
    0.70
     merchandise
    0.68
     kits
    0.68
     paraphernalia
    0.68
     utensils
    0.67
     goodies
    0.67
     stationery
    0.66
     memorabilia
    0.66
    Activations Density 0.275%

    No Known Activations