© 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. 3-GEMMASCOPE-RES-16K
    11. 15518
    Prev
    Next
    INDEX
    Explanations

    references to local communities and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.94
     présentée
    -0.75
    featureID
    -0.72
     springfox
    -0.70
     урна
    -0.69
     equivo
    -0.68
     Phry
    -0.67
    hasMoreElements
    -0.67
     mergeFrom
    -0.66
     Parole
    -0.65
    POSITIVE LOGITS
     local
    3.31
     Local
    2.99
    local
    2.95
    Local
    2.90
     LOCAL
    2.88
    LOCAL
    2.64
     locally
    2.46
     lokal
    2.38
     lokalen
    2.37
     lokale
    2.31
    Activations Density 0.054%

    No Known Activations