© 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. 22-GEMMASCOPE-RES-16K
    11. 8433
    Prev
    Next
    INDEX
    Explanations

    elements related to efficiency and optimization in processes

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

    "As" followed by an adverb (best, efficiently, early)

    np_acts-logits-general · gemini-2.0-flash

    as much as possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.79
     plötzlich
    -0.64
     suddenly
    -0.61
    Suddenly
    -0.56
    难怪
    -0.55
     Suddenly
    -0.55
     soudain
    -0.54
     autorytatywna
    -0.54
    suddenly
    -0.54
     ujednoznacz
    -0.52
    POSITIVE LOGITS
     möglichst
    1.94
    尽可能
    1.68
     cât
    1.54
    できるだけ
    1.46
     mahdollis
    1.45
     maximum
    1.45
     максимально
    1.41
    なるべく
    1.36
     zoveel
    1.32
     as
    1.30
    Activations Density 0.404%

    No Known Activations