© 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. 14928
    Prev
    Next
    INDEX
    Explanations

    references to relationships and social connections

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

    Informal internet language and punctuation

    np_acts-logits-general · gemini-2.0-flash

    informal language and punctuation

    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
    . 
    -1.43
     Covid
    -1.30
     COVID
    -1.24
    Covid
    -1.18
    COVID
    -1.16
     
    -1.13
     covid
    -1.13
     pandemia
    -1.12
    covid
    -1.07
    https
    -1.06
    POSITIVE LOGITS
     idéia
    1.33
     definately
    1.12
     daß
    0.95
     ^_^
    0.95
    myspace
    0.91
     fuckin
    0.88
     biß
    0.87
     -_-
    0.86
     freakin
    0.85
     Daß
    0.83
    Activations Density 1.918%

    No Known Activations