© 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. 1282
    Prev
    Next
    INDEX
    Explanations

    references to measurements, specifically in scientific contexts

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

    Conversion to/from litres or millilitres

    np_acts-logits-general · gemini-2.0-flash

    volume conversions and measurements

    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
    fromCharCode
    -0.61
    óry
    -0.60
     shingles
    -0.60
     Audiodateien
    -0.60
    原始内容存档于
    -0.59
     fumée
    -0.58
    Derbyniad
    -0.58
    WEBPACK
    -0.58
     IOError
    -0.57
     hickory
    -0.57
    POSITIVE LOGITS
     cup
    1.17
     cups
    1.09
     Cup
    1.01
     glass
    1.00
     drinking
    0.94
     gelas
    0.93
    Cup
    0.91
     Cups
    0.91
    cup
    0.88
    Drinking
    0.84
    Activations Density 0.290%

    No Known Activations