© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 56063
    Prev
    Next
    INDEX
    Explanations

    references to specific events or conferences related to the WWDC (Apple's Worldwide Developers Conference)

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

    WW, WWII, WWI, World War

    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
    styleType
    -0.65
    ogaster
    -0.65
    izr
    -0.63
    saraba
    -0.61
    orteur
    -0.60
    quartile
    -0.58
    parsedMessage
    -0.57
    bondale
    -0.56
    deri
    -0.56
    aitlin
    -0.56
    POSITIVE LOGITS
     WW
    1.98
    WW
    1.92
     ww
    1.68
    ww
    1.63
    Ww
    1.19
    WWW
    0.91
     WWII
    0.90
     WWI
    0.89
    World
    0.74
     WWW
    0.74
    Activations Density 0.005%

    No Known Activations