© 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. 11672
    Prev
    Next
    INDEX
    Explanations

    references to comparisons and contrasts in contexts involving advancements or qualities

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

    like "traditional" or "conventional"

    np_acts-logits-general · gemini-2.0-flash

    contrasting with conventional

    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
    setVerticalGroup
    -0.62
    ddots
    -0.55
    brigens
    -0.54
    czegó
    -0.52
    AntiForgeryToken
    -0.51
    ospatial
    -0.50
     GenerationType
    -0.49
    nitus
    -0.48
    wpdb
    -0.47
    CastException
    -0.46
    POSITIVE LOGITS
     conventional
    2.80
     traditional
    2.67
     normal
    2.47
     ordinary
    2.45
    traditional
    2.39
    conventional
    2.33
     regular
    2.26
     Conventional
    2.25
    Conventional
    2.24
     usual
    2.22
    Activations Density 2.018%

    No Known Activations