© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8638
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quantities and proportions related to groups or categories

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

    "of whom" or "of which"

    np_acts-logits-general · gemini-2.0-flash

    of which or of whom clauses

    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
     Paglinawan
    -0.69
     referenties
    -0.69
     Wikimedijinoj
    -0.66
     BrowserModule
    -0.65
    antMatchers
    -0.62
    Демографія
    -0.61
     urch
    -0.60
    rrggbb
    -0.58
    )_/¯
    -0.58
    masing
    -0.57
    POSITIVE LOGITS
     which
    1.41
    which
    1.08
     whom
    0.94
    Which
    0.91
     Which
    0.89
     WHICH
    0.87
     cuales
    0.77
     которых
    0.74
     whose
    0.71
     lesquels
    0.68
    Activations Density 0.094%

    No Known Activations