© 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. 11700
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and technical terms related to software development

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

    types or categories

    np_acts-logits-general · gemini-2.0-flash

    words called or named

    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
     سكانية
    -0.83
    writeFieldEnd
    -0.80
    twimg
    -0.74
     незавершена
    -0.74
    出版年
    -0.72
    -------------</
    -0.71
    RTEX
    -0.69
     متعلقه
    -0.66
    styleType
    -0.65
    httphttps
    -0.65
    POSITIVE LOGITS
     llamada
    0.93
     denominada
    0.91
     llamado
    0.85
    자인
    0.84
     denominado
    0.84
    ான
    0.79
     called
    0.79
    மான
    0.78
     olan
    0.78
    called
    0.78
    Activations Density 1.536%

    No Known Activations