© 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. 1208
    Prev
    Next
    INDEX
    Explanations

    elements related to buttons and links within HTML code

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

    before labels or tags in code or data

    np_acts-logits-general · gemini-2.0-flash

    seasonal FDR

    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
     dormitórios
    -0.42
    ...
    -0.39
    break
    -0.39
    {}{
    -0.39
    Hey
    -0.38
    ്ട
    -0.38
    pha
    -0.38
    bik
    -0.38
    ショ
    -0.37
    CHK
    -0.36
    POSITIVE LOGITS
     class
    1.11
    RenderAtEndOf
    0.91
     className
    0.91
     surla
    0.82
    TypedDataSet
    0.77
     classname
    0.76
    class
    0.76
     getClass
    0.75
    queryInterface
    0.74
    setVerticalGroup
    0.73
    Activations Density 0.056%

    No Known Activations