© 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. 20-GEMMASCOPE-RES-16K
    11. 6030
    Prev
    Next
    INDEX
    Explanations

    references to COVID-related topics

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

    "COVID" or "UTF"

    np_acts-logits-general · gemini-2.0-flash

    COVID-19 and UTF-8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.76
    verwijspagina
    -0.74
    oa̍t
    -0.67
    帖最后由
    -0.64
    Aiheesta
    -0.64
    
    -0.64
     estekak
    -0.62
    ètement
    -0.61
    RectangleBorder
    -0.61
    MLLoader
    -0.61
    POSITIVE LOGITS
    SuppressLint
    0.55
    1
    0.51
     noqa
    0.48
    (-
    0.48
    =-
    0.46
     teck
    0.43
    eternal
    0.43
    oost
    0.43
     arriv
    0.42
    urp
    0.42
    Activations Density 0.262%

    No Known Activations