© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14454
    Prev
    Next
    INDEX
    Explanations

    markers indicating the start of new sections or important entries in a text

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

    Code snippets/XML/Programming

    np_acts-logits-general · gemini-2.0-flash

    statistics and locations

    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
     createState
    -0.62
     يتيمه
    -0.59
     שוליים
    -0.58
     financières
    -0.49
    üks
    -0.49
     utom
    -0.48
     diren
    -0.48
     Gans
    -0.47
    transQ
    -0.47
     Miro
    -0.47
    POSITIVE LOGITS
    elemField
    0.68
    ANTLR
    0.64
     AssemblyTitle
    0.64
     ditto
    0.62
    Geplaatst
    0.62
     تضيفلها
    0.61
     likewise
    0.60
    Carriera
    0.60
     zase
    0.59
     ویکی‌پدی
    0.59
    Activations Density 0.363%

    No Known Activations