© 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. 16268
    Prev
    Next
    INDEX
    Explanations

    references related to programming and code structure, particularly in Java

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

    Code or file paths

    np_acts-logits-general · gemini-2.0-flash

    align 0-16

    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
    wie
    -0.49
     }_{
    -0.47
    şil
    -0.47
    unsqueeze
    -0.46
    koj
    -0.45
    initComponents
    -0.45
    StringUtils
    -0.44
    nonumber
    -0.43
    COD
    -0.43
    amata
    -0.43
    POSITIVE LOGITS
     للمعارف
    0.76
    orsese
    0.75
     дописавши
    0.74
    GEBURTS
    0.73
    MLLoader
    0.70
     betweenstory
    0.69
    ArrowToggle
    0.68
    पया
    0.67
     الحره
    0.66
    contentLoaded
    0.66
    Activations Density 0.155%

    No Known Activations