© 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. 12301
    Prev
    Next
    INDEX
    Explanations

    references to documentation or formal protocols

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

    Abbreviations in parentheses

    np_acts-logits-general · gemini-2.0-flash

    acronyms and abbreviations

    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
     raiſ
    -0.72
    SequentialGroup
    -0.70
     myſelf
    -0.64
     poffible
    -0.63
     Monfieur
    -0.63
     pleaſure
    -0.63
     ſever
    -0.63
     ſeveral
    -0.62
     виправивши
    -0.62
     فريبيس
    -0.60
    POSITIVE LOGITS
    MT
    0.94
    rt
    0.93
     MT
    0.92
    FT
    0.91
     RT
    0.90
    mt
    0.89
    BT
    0.89
    dt
    0.88
    RT
    0.86
     PT
    0.86
    Activations Density 1.000%

    No Known Activations