© 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. 18-GEMMASCOPE-RES-16K
    11. 9944
    Prev
    Next
    INDEX
    Explanations

    references to orchestras and musical directors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    time spans or locations

    np_acts-logits-general · gemini-2.0-flash

    during a period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.89
    Rüyada
    -0.75
    expandindo
    -0.72
     MenuView
    -0.72
    webElementXpaths
    -0.68
     الحره
    -0.67
    }{*}{
    -0.66
     NSCoder
    -0.66
    SequentialGroup
    -0.66
    ORROW
    -0.64
    POSITIVE LOGITS
     between
    1.10
    Between
    1.05
     perioden
    1.02
    between
    0.98
     Between
    0.98
     perioada
    0.90
     during
    0.88
     BETWEEN
    0.88
     الفترة
    0.84
     periode
    0.83
    Activations Density 0.446%

    No Known Activations