© 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. 24-GEMMASCOPE-RES-16K
    11. 5026
    Prev
    Next
    INDEX
    Explanations

    terms related to immune responses and inflammatory processes

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

    followed by "with" or "of"

    np_acts-logits-general · gemini-2.0-flash

    associated with biological conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    Not in Any Lists

    No Comments

    Negative Logits
     loob
    -0.45
    testens
    -0.41
    enumi
    -0.41
    živ
    -0.40
    💼
    -0.40
     speaking
    -0.39
     forget
    -0.39
     aikaa
    -0.38
     mund
    -0.38
     embar
    -0.38
    POSITIVE LOGITS
     inhibition
    0.80
     intracellular
    0.77
     physiologic
    0.77
     cytotoxic
    0.76
     physiological
    0.75
     antigen
    0.74
     pathogenic
    0.74
     transgenic
    0.73
     Inhibition
    0.73
     phenotypes
    0.72
    Activations Density 4.077%

    No Known Activations