© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 125102
    Prev
    Next
    INDEX
    Explanations

    terms related to paddle shifters and paddle-based controls in vehicles

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

    paddle or PDE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.61
     JsonConvert
    -0.60
    ibouti
    -0.58
     otomatig
    -0.58
    ariConfig
    -0.50
    basicConfig
    -0.50
     Fairfax
    -0.49
     архивлан
    -0.48
    mobileqq
    -0.48
     Westmoreland
    -0.47
    POSITIVE LOGITS
     paddle
    2.66
     Paddle
    2.38
    paddle
    2.34
    Paddle
    2.25
     paddles
    2.13
     paddling
    1.69
     padd
    1.55
    padd
    1.48
    桨
    0.89
     canoe
    0.84
    Activations Density 0.002%

    No Known Activations