© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1348
    Prev
    Next
    INDEX
    Explanations

    words related to legal cases and entities involved in trials

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

    Abbreviations/Acronyms

    np_acts-logits-general · gemini-2.0-flash

    scientific abbreviations and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.88
     nakalista
    -0.86
     дописавши
    -0.82
    AutoScaleMode
    -0.81
     consultato
    -0.81
    Personendaten
    -0.80
    aarrggbb
    -0.75
     ویکی‌پدی
    -0.70
     disambiguazione
    -0.70
     Paglinawan
    -0.69
    POSITIVE LOGITS
     AppColors
    0.62
     riuscito
    0.58
     cref
    0.58
     medu
    0.55
     stessa
    0.53
     وتسجيلات
    0.52
     medes
    0.52
     medesimo
    0.50
     Sra
    0.50
     leaſt
    0.48
    Activations Density 0.551%

    No Known Activations