© 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. 3728
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new document or section

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

    Tokens often followed by punctuation or mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    calculating probability

    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
     itſelf
    -1.06
     NUKAT
    -1.05
     Jefus
    -1.03
    ſelves
    -1.02
    RectangleBorder
    -1.00
     kasarigan
    -1.00
     '\\;'
    -0.99
     tartalomajánló
    -0.99
    AccessorTable
    -0.98
     Roskov
    -0.97
    POSITIVE LOGITS
    ,
    0.48
     to
    0.47
     ne
    0.44
     o
    0.43
     in
    0.42
     by
    0.41
     from
    0.38
     with
    0.37
     for
    0.37
    !
    0.36
    Activations Density 0.012%

    No Known Activations