© 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. 1257
    Prev
    Next
    INDEX
    Explanations

    specific numeric data points and mathematical expressions

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

    Numbers followed by a digit

    np_acts-logits-general · gemini-2.0-flash

    five

    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
     الحره
    -0.71
     Eighth
    -0.59
     resourceCulture
    -0.57
     eighth
    -0.55
    8
    -0.55
     VIII
    -0.55
     Eight
    -0.54
    tonsoft
    -0.50
    autoconfigure
    -0.50
    八
    -0.49
    POSITIVE LOGITS
    findpost
    0.64
    ⑤
    0.61
     Fifth
    0.59
     Chwiliwch
    0.57
     five
    0.57
     ५
    0.57
     FIFTH
    0.56
     fifth
    0.55
     fünf
    0.54
    5
    0.54
    Activations Density 0.534%

    No Known Activations