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. 2893
    Prev
    Next
    INDEX
    Explanations

    references to severe weather events and their impacts

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

    Weather events/phenomena

    np_acts-logits-general · gemini-2.0-flash

    hurricanes and storms

    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
     henvisninger
    -0.58
    Diweddarwch
    -0.56
     سكانية
    -0.54
    webElementXpaths
    -0.54
    Портал
    -0.53
    autique
    -0.51
    setAccessible
    -0.51
    acchar
    -0.51
    itettura
    -0.51
     Shooting
    -0.51
    POSITIVE LOGITS
     storm
    1.11
     Storm
    0.99
     tornado
    0.96
     storms
    0.94
    storm
    0.93
     tornadoes
    0.91
    Storm
    0.89
     hurricane
    0.85
     Hurricane
    0.84
     Tornado
    0.82
    Activations Density 0.128%

    No Known Activations