© 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. 14-GEMMASCOPE-RES-16K
    11. 8969
    Prev
    Next
    INDEX
    Explanations

    specific symbols, punctuation, or formatting used in written language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.66
     iNdEx
    -0.60
     كومونز
    -0.57
    Revenir
    -0.52
     ProtoMessage
    -0.50
    CppCodeGen
    -0.50
    alsey
    -0.49
     Polic
    -0.46
    다고
    -0.45
     onCancelled
    -0.44
    POSITIVE LOGITS
     مشين
    0.76
     giggled
    0.63
     giggle
    0.63
     kasarigan
    0.62
     laugh
    0.60
    ShouldBe
    0.59
     متعلقه
    0.58
    piram
    0.56
    TypedDataSet
    0.55
     ***!
    0.54
    Activations Density 0.042%

    No Known Activations