© 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. 16112
    Prev
    Next
    INDEX
    Explanations

    references to time and events following a specific sequence or duration

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

    Following "a" and describing a time period

    np_acts-logits-general · gemini-2.0-flash

    after a descriptor

    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
     prochaines
    -0.67
    ต่อไป
    -0.64
    出版年
    -0.62
     tillgäng
    -0.62
     jöv
    -0.61
     futuras
    -0.61
     prossima
    -0.60
    potensi
    -0.59
    ercito
    -0.58
     henceforth
    -0.56
    POSITIVE LOGITS
     unsuccessful
    1.08
     stint
    1.03
     successful
    1.00
     brief
    0.98
     years
    0.97
     failed
    0.95
     lengthy
    0.92
     disastrous
    0.89
     tumultuous
    0.86
    successful
    0.84
    Activations Density 0.354%

    No Known Activations