© 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. 10404
    Prev
    Next
    INDEX
    Explanations

    references to natural disasters and the responses to them

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

    Follows the word "an" or "in"

    np_acts-logits-general · gemini-2.0-flash

    words before accidents

    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
    findpost
    -0.71
    IBOutlet
    -0.69
    ThroughAttribute
    -0.65
    ponses
    -0.65
    MarshalTo
    -0.64
    Sucesor
    -0.63
    المشاركات
    -0.61
    umpulkan
    -0.60
    Tikang
    -0.59
     immortality
    -0.59
    POSITIVE LOGITS
     fires
    1.16
     earthquakes
    1.11
     floods
    1.07
     earthquake
    1.07
     wildfires
    1.04
     storms
    0.94
     fire
    0.93
     disaster
    0.93
     storm
    0.92
     hurricane
    0.92
    Activations Density 0.343%

    No Known Activations