© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6673
    Prev
    Next
    INDEX
    Explanations

    references to immune system components and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Immune cell types or markers

    np_acts-logits-general · gemini-2.0-flash

    immune cells, cytokines, and receptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adamson
    -0.52
     Petron
    -0.52
     '\\;'
    -0.51
     Beal
    -0.50
    маль
    -0.47
    createStatement
    -0.47
     Victims
    -0.47
    ocarpus
    -0.47
     cilia
    -0.46
    drivers
    -0.45
    POSITIVE LOGITS
     Immunol
    0.75
     Immunology
    0.75
     immunosupp
    0.71
     MHC
    0.70
     HLA
    0.68
     immunological
    0.64
    PerformLayout
    0.63
     immunos
    0.62
     lymphoid
    0.61
     linkovi
    0.61
    Activations Density 1.622%

    No Known Activations