© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-GEMMASCOPE-RES-16K
    11. 5589
    Prev
    Next
    INDEX
    Explanations

    keywords related to events, news, and reviews in a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.80
    bisoft
    -0.48
    adpleegd
    -0.47
     Wikimédia
    -0.45
    PyExc
    -0.45
    databind
    -0.44
    وحة
    -0.44
     مؤرشف
    -0.44
     démocr
    -0.44
    AccessorTable
    -0.43
    POSITIVE LOGITS
     hebdomada
    0.65
     roundup
    0.64
     Feature
    0.59
     mergeFrom
    0.59
    Feature
    0.58
    weekly
    0.57
     actionPerformed
    0.56
     weekly
    0.56
    feature
    0.56
    Digest
    0.55
    Activations Density 0.217%

    No Known Activations