© 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. 20-GEMMASCOPE-RES-16K
    11. 3935
    Prev
    Next
    INDEX
    Explanations

    aspects related to regulatory policies and their implications for competition and law enforcement

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

    Follows "of", "on", or "in"

    np_acts-logits-general · gemini-2.0-flash

    ad hoc network

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     folks
    -0.66
     isn
    -0.51
     súper
    -0.47
     aren
    -0.46
    wesenheit
    -0.46
     we
    -0.46
     weird
    -0.45
    Percent
    -0.45
     Texas
    -0.45
     USDA
    -0.45
    POSITIVE LOGITS
     envisaged
    1.04
     Reverso
    0.97
     colourless
    0.91
     Roskov
    0.90
    colours
    0.86
     favourably
    0.85
     autorytatywna
    0.84
    AddHtmlAttribute
    0.84
     envisage
    0.84
    personalised
    0.83
    Activations Density 0.280%

    No Known Activations