© 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. 4-GEMMASCOPE-RES-16K
    6. 130
    Prev
    Next
    INDEX
    Explanations

    references to entities and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.76
     Paglinawan
    -0.69
     nakalista
    -0.68
     ویکی‌پدیای
    -0.67
     propOrder
    -0.65
     MainAxisSize
    -0.65
    <bos>
    -0.64
     Odys
    -0.62
     xenia
    -0.62
    تقاوى
    -0.61
    POSITIVE LOGITS
     White
    0.56
    high
    0.56
     dei
    0.55
    isNameExpr
    0.54
     zahlreichen
    0.54
     numerosos
    0.53
     High
    0.52
     numerosas
    0.52
     many
    0.52
     high
    0.51
    Activations Density 1.270%

    No Known Activations