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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3737
    Prev
    Next
    INDEX
    Explanations

    terms related to cytokines and their roles in immune responses

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

    Cytokines, especially interleukins (IL) and interferons (IFN)

    np_acts-logits-general · gemini-2.0-flash

    interleukins and interferons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sap
    -0.53
     spese
    -0.52
    sap
    -0.52
     säll
    -0.51
     kautta
    -0.51
     tatuagem
    -0.50
     AdapterView
    -0.49
    Personendaten
    -0.49
     canali
    -0.48
     sæ
    -0.48
    POSITIVE LOGITS
     cytokines
    0.96
     cytokine
    0.85
     interleukin
    0.75
    tokine
    0.72
    yntaxException
    0.70
     secreted
    0.69
     secretion
    0.64
     IL
    0.63
     growth
    0.62
     Secre
    0.62
    Activations Density 0.996%

    No Known Activations