© 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. 3510
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or a new section

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

    Code, symbols, or non-English text

    np_acts-logits-general · gemini-2.0-flash

    special characters and code snippets

    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
    pern
    -0.52
    rag
    -0.47
    dela
    -0.46
    dei
    -0.46
     imp
    -0.45
    delo
    -0.44
    da
    -0.43
    ikan
    -0.43
    ries
    -0.42
     Devlin
    -0.42
    POSITIVE LOGITS
     الحره
    0.90
     >=",
    0.78
     متعلقه
    0.71
    DockStyle
    0.68
    siąż
    0.65
    adecimal
    0.63
    )++;
    0.63
    rungsseite
    0.62
     itſelf
    0.62
    ackerel
    0.61
    Activations Density 0.031%

    No Known Activations