Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9372
    Prev
    Next
    INDEX
    Explanations

    details about severe weather conditions, specifically tornadoes and forecasts

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

    Weather conditions, especially wind and storms

    np_acts-logits-general · gemini-2.0-flash

    weather forecasts and conditions

    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
     فريبيس
    -0.76
    UserScript
    -0.64
     AssemblyCulture
    -0.53
    apiVersion
    -0.52
    GraphicsUnit
    -0.50
    الدراسه
    -0.49
    ̣c
    -0.49
     isEqual
    -0.48
    Shit
    -0.47
     Peraturan
    -0.47
    POSITIVE LOGITS
     overnight
    0.68
     scattered
    0.64
     patchy
    0.63
    Overnight
    0.63
     mostly
    0.59
     Overnight
    0.58
     Temperatures
    0.58
    OVERN
    0.58
     '\\;'
    0.58
    balleur
    0.56
    Activations Density 0.072%

    No Known Activations