Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11816
    Prev
    Next
    INDEX
    Explanations

    statistical terms and metrics related to regression analysis

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

    Mathematical symbols (chi, R) and exponents

    np_acts-logits-general · gemini-2.0-flash

    chi-squared and R-squared statistics

    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
     دیکھیے
    -0.66
    esez
    -0.66
    WriteLiteral
    -0.58
    }{*}{
    -0.57
    jelen
    -0.55
     Vikipedi
    -0.54
    IsContent
    -0.54
     henvisninger
    -0.52
    发表于
    -0.52
    IVEREF
    -0.51
    POSITIVE LOGITS
     square
    1.64
     squared
    1.53
     Square
    1.46
    Square
    1.44
    square
    1.41
     squares
    1.40
    ^
    1.35
     SQUARE
    1.34
    SQUARE
    1.27
    squared
    1.26
    Activations Density 1.704%

    No Known Activations