© 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. 18-GEMMASCOPE-RES-16K
    11. 8223
    Prev
    Next
    INDEX
    Explanations

    concepts related to environmental protection, specifically concerning air quality and ozone regulation

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

    after environmental terms

    np_acts-logits-general · gemini-2.0-flash

    air quality, ozone, water clearness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.71
     محفوظة
    -0.57
    HasForeignKey
    -0.56
    abspath
    -0.54
    dion
    -0.51
    hical
    -0.49
    ätigkeit
    -0.48
    HasIndex
    -0.47
    تقاوى
    -0.47
     COAST
    -0.47
    POSITIVE LOGITS
    Качество
    0.77
     clearness
    0.69
     itſelf
    0.65
     Purity
    0.64
     Pebble
    0.64
     Anſ
    0.64
     nahilalakip
    0.63
     bakter
    0.63
     ―――――
    0.63
     Klar
    0.61
    Activations Density 0.080%

    No Known Activations