© 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. 1990
    Prev
    Next
    INDEX
    Explanations

    financial data and economic metrics

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

    Numbers followed by a larger number

    np_acts-logits-general · gemini-2.0-flash

    large numerical quantities

    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
    AsUp
    -1.12
    ArrowToggle
    -1.11
    MemoryWarning
    -1.04
    mybatisplus
    -1.01
    MessageTagHelper
    -0.99
    存于互联网档案馆
    -0.99
    BeginInit
    -0.92
    MLLoader
    -0.90
    SequentialGroup
    -0.88
     كومونز
    -0.88
    POSITIVE LOGITS
     million
    0.81
     thousands
    0.77
     millions
    0.77
     billion
    0.73
     thousand
    0.65
     billions
    0.64
    million
    0.60
     trillion
    0.59
     hundreds
    0.54
     Million
    0.54
    Activations Density 1.987%

    No Known Activations