© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8634
    Prev
    Next
    INDEX
    Explanations

    mentions of the letter "U" in various contexts

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

    "U.S." followed by patent information

    np_acts-logits-general · gemini-2.0-flash

    U.S

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ServiceException
    -0.52
    NOPQRST
    -0.48
    basicConfig
    -0.46
    tilage
    -0.44
    AnimationsModule
    -0.44
     деле
    -0.43
     Pul
    -0.42
    끄
    -0.42
     Investigaciones
    -0.42
    orsese
    -0.42
    POSITIVE LOGITS
     HasFactory
    0.70
     zelve
    0.67
     للاسماء
    0.65
    SuccessListener
    0.63
    orianCalendar
    0.62
    LookAnd
    0.61
    sizeCache
    0.61
    CppMethod
    0.60
     Colombie
    0.60
     jsPsych
    0.60
    Activations Density 0.134%

    No Known Activations