© 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. 3466
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic and financial metrics

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

    a reduction in quantity

    np_acts-logits-general · gemini-2.0-flash

    fewer or less

    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
    glEnable
    -0.60
    دانشنامهٔ
    -0.55
    moveToNext
    -0.54
    yntaxException
    -0.54
    (++
    -0.52
     enlarge
    -0.51
    ++
    -0.50
    Bigger
    -0.49
     (++
    -0.49
     Larger
    -0.49
    POSITIVE LOGITS
     reduced
    2.07
    reduced
    1.87
     Reduced
    1.82
    Reduced
    1.80
     reduction
    1.78
     fewer
    1.76
     less
    1.74
     decreased
    1.72
     Fewer
    1.72
     Less
    1.70
    Activations Density 1.535%

    No Known Activations