© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 44642
    Prev
    Next
    INDEX
    Explanations

    references to natural killer (NK) cells in the context of immune response

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

    natural killer cells

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    السكان
    -0.56
    DockStyle
    -0.54
     Fallon
    -0.52
    ::_('
    -0.52
    ISODE
    -0.52
    setopt
    -0.52
     Geller
    -0.51
     getApplication
    -0.50
     Avila
    -0.50
    DriverManager
    -0.50
    POSITIVE LOGITS
     NK
    2.30
    NK
    2.14
     nk
    1.52
    nk
    1.48
     Nk
    1.37
    Nk
    1.26
    INK
    0.73
     NKC
    0.67
    НК
    0.66
    Ink
    0.66
    Activations Density 0.008%

    No Known Activations