© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7194
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and data representations in scientific contexts

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

    Numbers within a plus/minus range

    np_acts-logits-general · gemini-2.0-flash

    quantities and ranges

    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
     hundred
    -0.80
     Thirty
    -0.77
     Eighty
    -0.76
    Thirty
    -0.75
     Twenty
    -0.73
    Twenty
    -0.71
     eighty
    -0.71
     Fifty
    -0.70
     Seventy
    -0.70
     seventy
    -0.70
    POSITIVE LOGITS
     four
    1.10
     three
    1.04
     five
    1.00
    three
    1.00
     quatre
    0.99
    four
    0.96
     trois
    0.96
     quatro
    0.94
    Three
    0.91
     fyra
    0.89
    Activations Density 1.405%

    No Known Activations