© 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. 14833
    Prev
    Next
    INDEX
    Explanations

    references to "Pu" related terms, likely indicative of a software or programming context

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

    "Pu" or "pu" tokens

    np_acts-logits-general · gemini-2.0-flash

    Pu with Puromycin, PuTTY, Puccini

    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
     Normdatei
    -0.70
    abestanden
    -0.68
     étoit
    -0.66
    Brainz
    -0.65
     commerciali
    -0.64
    WriteTagHelper
    -0.62
     Wiktionnaire
    -0.61
    BarStyle
    -0.59
     Reverso
    -0.59
    wnież
    -0.59
    POSITIVE LOGITS
     Pu
    0.66
     Pus
    0.62
     pu
    0.61
    Pu
    0.59
    UseVisualStyle
    0.58
    peteer
    0.55
     Puy
    0.53
    rrggbb
    0.51
     pulls
    0.48
    intended
    0.47
    Activations Density 0.111%

    No Known Activations