© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11581
    Prev
    Next
    INDEX
    Explanations

    non-alphanumeric symbols or punctuation and their usage in various contexts

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

    TeX markup and special characters

    np_acts-logits-general · gemini-2.0-flash

    closing 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
    ные
    -0.66
    ending
    -0.63
    ных
    -0.57
    al
    -0.56
    Ars
    -0.54
    gabe
    -0.54
    ed
    -0.54
    ات
    -0.53
     sorte
    -0.53
    ли
    -0.53
    POSITIVE LOGITS
     للمعارف
    0.83
    />";
    0.82
    ^(@)
    0.81
     >=",
    0.80
    tagext
    0.79
     contextLoads
    0.78
    IActionResult
    0.77
     Jefus
    0.76
     myſelf
    0.74
    awtextra
    0.72
    Activations Density 0.893%

    No Known Activations