© 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 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. 8585
    Prev
    Next
    INDEX
    Explanations

    structured programming concepts and parameters in code

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

    Filtering or limiting search results/options

    np_acts-logits-general · gemini-2.0-flash

    filtering parameters

    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
     nahilalakip
    -0.80
     newNode
    -0.61
    Chham
    -0.61
     AssemblyProduct
    -0.57
     సౌకర్య
    -0.56
    oplast
    -0.55
     kasarigan
    -0.52
    ➟
    -0.52
     newItem
    -0.52
     otomatig
    -0.51
    POSITIVE LOGITS
     filter
    1.54
     filters
    1.52
     Filter
    1.37
    Filter
    1.36
     Filters
    1.34
     filtering
    1.29
    filter
    1.29
     filtre
    1.27
    filters
    1.24
     filtro
    1.22
    Activations Density 0.289%

    No Known Activations