© 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. 1143
    Prev
    Next
    INDEX
    Explanations

    references to deserts and drought-affected areas

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

    deserts or arid environments

    np_acts-logits-general · gemini-2.0-flash

    arid desert regions

    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
     aortic
    -0.65
     zebrafish
    -0.65
    ########.
    -0.59
     downstairs
    -0.58
    sizeCache
    -0.57
    TreeNode
    -0.57
     Penang
    -0.56
     balık
    -0.55
     ISTAT
    -0.54
    batore
    -0.54
    POSITIVE LOGITS
     desert
    1.56
     Desert
    1.50
    Desert
    1.37
    desert
    1.32
     deserts
    1.16
     sand
    1.15
    沙漠
    1.09
     dunes
    1.09
     désert
    1.09
     deserto
    1.06
    Activations Density 0.212%

    No Known Activations