© 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. 12316
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and control flow statements

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

    Code snippets iterating with `i++` or `i=0`

    np_acts-logits-general · gemini-2.0-flash

    code tokens and structure

    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
     =>
    -0.51
    führt
    -0.48
     plaît
    -0.48
    disposing
    -0.48
    führen
    -0.47
    жка
    -0.45
     reason
    -0.44
    '],'
    -0.44
     Likewise
    -0.43
    wikkeld
    -0.43
    POSITIVE LOGITS
    NameInMap
    0.77
     resourceCulture
    0.77
    ImageContext
    0.74
    تقاوى
    0.74
     utafitiHapana
    0.73
    ReusableCell
    0.72
     Wikimedijinoj
    0.72
     تضيفلها
    0.69
    DeleteBehavior
    0.68
    SharedDtor
    0.68
    Activations Density 0.123%

    No Known Activations