© 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. 9314
    Prev
    Next
    INDEX
    Explanations

    references to scientific processes and experimental results related to viral infections

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

    before ", was", "of", or "with"

    np_acts-logits-general · gemini-2.0-flash

    entities with states or changes

    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
     تضيفلها
    -0.78
    AndEndTag
    -0.72
    esModule
    -0.69
    webElementGuid
    -0.69
    ViewFeatures
    -0.66
    imédia
    -0.60
     ExecuteAsync
    -0.60
    ubehör
    -0.59
    liothèque
    -0.59
    ContextHolder
    -0.59
    POSITIVE LOGITS
     machines
    1.03
     devices
    0.98
     vehicles
    0.98
     animals
    0.96
     objects
    0.91
     organisms
    0.91
     vessels
    0.89
     items
    0.88
     organism
    0.86
     products
    0.85
    Activations Density 1.268%

    No Known Activations