© 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. 22-GEMMASCOPE-RES-16K
    11. 10036
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "cytokine" and its various related forms

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

    starting with "Cy" or "cy"

    np_acts-logits-general · gemini-2.0-flash

    words starting with cy

    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
    ⓘ
    -0.70
    RetentionPolicy
    -0.60
    NavController
    -0.57
    abestanden
    -0.56
    #+#
    -0.56
    GRANTED
    -0.56
    脚注の使い方
    -0.54
     BorderRadius
    -0.52
     BorderSide
    -0.52
     estekak
    -0.51
    POSITIVE LOGITS
     Cy
    0.80
     cy
    0.76
     CY
    0.67
    Cy
    0.61
     Cyr
    0.57
    cy
    0.53
    cluye
    0.50
     Cypri
    0.49
    <tbody>
    0.49
     cytos
    0.48
    Activations Density 0.139%

    No Known Activations