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. 19-GEMMASCOPE-RES-16K
    6. 1938
    Prev
    Next
    INDEX
    Explanations

    variables related to weather data models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.81
     فريبيس
    -0.79
    WebElementEntity
    -0.74
    WithIOException
    -0.66
    ValueStyle
    -0.64
     otomatig
    -0.62
    ViewFeatures
    -0.61
    Portály
    -0.60
    bcryptjs
    -0.60
     ISNI
    -0.59
    POSITIVE LOGITS
     weather
    1.33
     Weather
    1.22
     meteorological
    1.20
    Weather
    1.19
    weather
    1.16
     meteoro
    1.10
     WEATHER
    1.08
    WEATHER
    1.04
     Meteorological
    0.98
     Meteoro
    0.90
    Activations Density 0.173%

    No Known Activations