© 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. 0-GEMMASCOPE-RES-16K
    11. 7499
    Prev
    Next
    INDEX
    Explanations

    references to specific visual attributes or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -1.05
     estekak
    -1.01
     Roskov
    -0.96
     bezeichneter
    -0.96
    oa̍t
    -0.95
     مشين
    -0.94
    abestanden
    -0.94
    Autoritní
    -0.91
     photolibrary
    -0.90
    Искәрмәләр
    -0.88
    POSITIVE LOGITS
     Cla
    0.78
     et
    0.73
    alt
    0.70
    Cla
    0.70
     cla
    0.63
     alt
    0.62
    cla
    0.61
     And
    0.60
    adas
    0.60
     Old
    0.57
    Activations Density 0.305%

    No Known Activations