Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15018
    Prev
    Next
    INDEX
    Explanations

    terms related to immune system mechanisms and responses, particularly involving macrophages and inflammatory pathways

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

    Immune cell activity

    np_acts-logits-general · gemini-2.0-flash

    immune cell activity and pathways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.89
     Monfieur
    -0.82
     Jefus
    -0.78
     intptr
    -0.77
     ujednoznacz
    -0.73
     Ause
    -0.72
     Efq
    -0.70
     дописавши
    -0.69
    mée
    -0.69
    awtextra
    -0.69
    POSITIVE LOGITS
    providedIn
    0.61
     responsible
    0.60
     responsáveis
    0.60
    BatchNorm
    0.57
    textTheme
    0.56
     cells
    0.53
     involucrados
    0.50
     odpowiedzial
    0.50
     responsables
    0.49
     pathways
    0.48
    Activations Density 1.230%

    No Known Activations