© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9375
    Prev
    Next
    INDEX
    Explanations

    the presence of "ur" as a significant substring in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConverterFactory
    -0.63
    참고
    -0.61
    ophosphate
    -0.60
    AUTHORS
    -0.59
     Radioactive
    -0.57
    webElementXpaths
    -0.57
    zeppelin
    -0.57
    Aix
    -0.57
    slide
    -0.57
     autorytatywna
    -0.55
    POSITIVE LOGITS
    ur
    2.67
    UR
    2.41
    ure
    2.14
    ura
    2.13
    urs
    1.83
    uren
    1.81
    URA
    1.80
    URE
    1.77
    ures
    1.71
     ur
    1.69
    Activations Density 0.176%

    No Known Activations