© 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. 3798
    Prev
    Next
    INDEX
    Explanations

    code elements related to programming syntax and data structures

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

    Code snippets and punctuation

    np_acts-logits-general · gemini-2.0-flash

    sugar Ado analogues

    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
    heden
    -0.54
    cellaneous
    -0.54
    OLPH
    -0.53
    encodeWith
    -0.52
     lenker
    -0.49
     Carrasco
    -0.47
    ERIES
    -0.47
    δέ
    -0.47
    Enllaces
    -0.47
    ngilizce
    -0.46
    POSITIVE LOGITS
    begin
    0.61
    期刊论文
    0.53
     <=",
    0.53
    const
    0.52
     begin
    0.52
    DebuggerNonUser
    0.52
    ItemBackground
    0.50
     ITER
    0.49
    Diwedd
    0.49
    .__
    0.48
    Activations Density 0.271%

    No Known Activations