© 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. 20-GEMMASCOPE-RES-16K
    11. 4478
    Prev
    Next
    INDEX
    Explanations

    terms related to weather and climate data

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

    weather and temperature data

    np_acts-logits-general · gemini-2.0-flash

    weather station and forecasts

    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
    WebElementEntity
    -0.74
    StoryboardSegue
    -0.66
     SPIE
    -0.65
     فريبيس
    -0.65
     otomatig
    -0.64
    WithIOException
    -0.64
    ValueStyle
    -0.64
    ViewFeatures
    -0.58
    ftagPool
    -0.55
    LogFactory
    -0.51
    POSITIVE LOGITS
     weather
    1.51
     Weather
    1.38
    Weather
    1.33
     meteorological
    1.30
    weather
    1.29
     meteoro
    1.24
     WEATHER
    1.21
    WEATHER
    1.19
     Meteorological
    1.15
     Meteoro
    1.11
    Activations Density 0.163%

    No Known Activations