© 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. 5-GEMMASCOPE-RES-16K
    11. 7224
    Prev
    Next
    INDEX
    Explanations

    terms related to natural disasters and weather phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.54
     muualla
    -0.51
    roit
    -0.50
    assertj
    -0.50
    obacz
    -0.49
    sibly
    -0.46
    vsky
    -0.46
    LogFactory
    -0.45
    Diweddarwch
    -0.44
    tria
    -0.44
    POSITIVE LOGITS
     storm
    1.25
     storms
    1.25
     hurricane
    1.19
     Hurricane
    1.18
     weather
    1.17
     meteoro
    1.16
    ricanes
    1.16
    Hurricane
    1.13
     Cyclone
    1.11
    storm
    1.11
    Activations Density 0.396%

    No Known Activations