© 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. 10-GEMMASCOPE-RES-16K
    11. 5843
    Prev
    Next
    INDEX
    Explanations

    numerical data, specifically related to years, statistics, and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.79
     '\\;'
    -0.78
     للمعارف
    -0.76
    WebElementEntity
    -0.73
    Ĝ
    -0.69
    تقاوى
    -0.67
    aarrggbb
    -0.65
     guangdong
    -0.64
    /*---
    -0.64
    цездатний
    -0.63
    POSITIVE LOGITS
     EconPapers
    0.54
     Others
    0.54
     Ibid
    0.49
    tiere
    0.45
    ='';
    0.44
    *);
    0.44
    DeleteMapping
    0.43
    reathe
    0.43
    oldt
    0.43
    ktır
    0.43
    Activations Density 0.658%

    No Known Activations