© 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. 13-GEMMASCOPE-RES-16K
    11. 1081
    Prev
    Next
    INDEX
    Explanations

    specialized code language elements and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.92
     Roskov
    -0.91
    Hentet
    -0.88
     متعلقه
    -0.86
    expandindo
    -0.77
     ExecuteAsync
    -0.75
    Tikang
    -0.72
     <=",
    -0.71
     ProtoMessage
    -0.71
    bootstrapcdn
    -0.68
    POSITIVE LOGITS
     تضيفلها
    0.63
    Geplaatst
    0.51
    WriteTagHelper
    0.50
    tubers
    0.49
    Tē
    0.46
     Gj
    0.45
    classnames
    0.44
    errHandler
    0.43
    upati
    0.42
    atzung
    0.41
    Activations Density 1.211%

    No Known Activations