© 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. 19-GEMMASCOPE-RES-16K
    11. 3715
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate referential expressions or specific mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eneuve
    -0.65
    ArrowToggle
    -0.61
     ujednoznacz
    -0.61
     Wiktionnaire
    -0.59
     kaynağından
    -0.59
     next
    -0.59
    ukone
    -0.58
    KommentareTeilen
    -0.56
    WithIOException
    -0.54
     Crossword
    -0.54
    POSITIVE LOGITS
     equipments
    0.59
     researches
    0.58
     StatelessWidget
    0.57
    spyOn
    0.56
    Портал
    0.54
     sufferings
    0.54
    tonsoft
    0.53
     geslacht
    0.53
    AxisAlignment
    0.52
     kind
    0.51
    Activations Density 0.234%

    No Known Activations