© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 10351
    Prev
    Next
    INDEX
    Explanations

    terms related to wrestling matches and victory outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.54
    ंदीखरीदारी
    -0.52
    +:+
    -0.50
     AssemblyTitle
    -0.50
     InputDecoration
    -0.48
    演奏
    -0.47
    archiviato
    -0.47
    awtextra
    -0.46
     Played
    -0.45
     jugador
    -0.45
    POSITIVE LOGITS
     wrestling
    1.43
     wrestle
    1.32
     wrestled
    1.30
     wrestlers
    1.27
     Wrestling
    1.24
     wrestler
    1.23
    Wrestling
    1.13
     wrest
    1.00
     grappling
    0.90
    restling
    0.86
    Activations Density 0.088%

    No Known Activations