© 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. 3426
    Prev
    Next
    INDEX
    Explanations

    references to competence and authority associated with tribal affiliations

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

    preceding "than"

    np_acts-logits-general · gemini-2.0-flash

    more... than

    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
     MainAxisSize
    -0.51
    ?></
    -0.50
    ViewImports
    -0.49
    Архівовано
    -0.49
    Ibid
    -0.48
    itinéraire
    -0.48
    visející
    -0.47
     دیکھیے
    -0.47
    pfung
    -0.46
     مصرى
    -0.46
    POSITIVE LOGITS
     than
    2.74
     THAN
    1.84
    than
    1.74
    Than
    1.70
     Than
    1.65
     niż
    1.61
     än
    1.48
    жели
    1.47
     kuin
    1.45
    THAN
    1.35
    Activations Density 0.372%

    No Known Activations