© 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. 16213
    Prev
    Next
    INDEX
    Explanations

    intensifiers that suggest a high level of quality or recommendation

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

    Follows "highly" and describes an adjective

    np_acts-logits-general · gemini-2.0-flash

    highly followed by adjective

    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
     aveug
    -0.77
     épu
    -0.62
     disparu
    -0.61
    toarele
    -0.60
     assolu
    -0.60
     détru
    -0.60
     effray
    -0.60
     perpétu
    -0.58
     extérieurs
    -0.57
     neutre
    -0.57
    POSITIVE LOGITS
     nakalista
    0.74
     estimés
    0.73
    SourceChecksum
    0.72
    ItemBackground
    0.64
    Personensuche
    0.64
    AutoScale
    0.62
    HtmlAttribute
    0.59
    EndGlobalSection
    0.59
    #+#
    0.58
    تقاوى
    0.57
    Activations Density 0.122%

    No Known Activations