© 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. 8-GEMMASCOPE-RES-16K
    11. 5221
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -1.09
    ">//
    -1.04
     kasarigan
    -1.02
    InjectAttribute
    -0.94
     الرياضيه
    -0.93
    bootstrapcdn
    -0.93
     &___
    -0.90
    featureID
    -0.90
    addCriterion
    -0.89
    yntaxException
    -0.89
    POSITIVE LOGITS
    td
    1.98
     td
    1.25
     colspan
    1.17
    TD
    1.00
    Td
    0.86
     rowspan
    0.76
     TD
    0.72
    tds
    0.63
    ++
    0.59
    getCell
    0.58
    Activations Density 0.012%

    No Known Activations