© 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. 21-GEMMASCOPE-RES-16K
    11. 2406
    Prev
    Next
    INDEX
    Explanations

    references to the "Ze" prefix in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.65
    istoitu
    -0.61
     MainAxisSize
    -0.60
    '},
    -0.60
    uxxxx
    -0.59
    mobileqq
    -0.59
     ویکی‌پدی
    -0.58
    MENAFN
    -0.56
    ."]
    -0.55
    KURZBESCHREIBUNG
    -0.54
    POSITIVE LOGITS
     Ze
    0.59
    Ze
    0.53
     roleId
    0.51
     zel
    0.49
    ■
    0.48
    phy
    0.45
     ghép
    0.45
     Zone
    0.44
    Zé
    0.44
    EFAULT
    0.43
    Activations Density 0.079%

    No Known Activations