© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117597
    Prev
    Next
    INDEX
    Explanations

    references to the 'rx' and 'RX' terms, which are commonly associated with data communication and acknowledgments in technical contexts

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

    rx and tx data/commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    儡
    -0.50
     “
    -0.47
     piece
    -0.45
    anager
    -0.45
    ClientSize
    -0.44
    مند
    -0.42
    AEL
    -0.42
     […]
    -0.42
     tem
    -0.41
     Neve
    -0.40
    POSITIVE LOGITS
    rx
    1.21
     Rx
    1.13
    Rx
    1.12
     RX
    1.12
    RX
    1.09
     rx
    1.05
    jaqueta
    0.74
    reactivex
    0.69
    kjø
    0.67
     Nax
    0.64
    Activations Density 0.009%

    No Known Activations