© 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. 16-GEMMASCOPE-RES-16K
    11. 8258
    Prev
    Next
    INDEX
    Explanations

    instances of the word "simple" and phrases that describe simplicity

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

    simplicity

    np_acts-logits-general · gemini-2.0-flash

    simple and uncomplicated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBarButtonItem
    -0.80
     passim
    -0.79
     AssemblyCompany
    -0.66
    InputBorder
    -0.65
    @@@@@@@@
    -0.65
    timbangkan
    -0.65
    edero
    -0.64
     turquesa
    -0.62
    hyrchwyd
    -0.61
    MLLoader
    -0.61
    POSITIVE LOGITS
     SIMPLE
    1.09
    SIMPLE
    1.00
     simple
    0.99
     Simple
    0.97
    Simple
    0.91
     Plain
    0.89
     uncomplicated
    0.87
     simpl
    0.83
    simple
    0.82
     Simplicity
    0.82
    Activations Density 0.091%

    No Known Activations