© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 3814
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to competitive outcomes and victories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    исленность
    -0.64
    czaj
    -0.60
    ArgumentParser
    -0.57
    IMPORTED
    -0.55
    HtmlAttribute
    -0.54
    acherous
    -0.53
    ibatis
    -0.53
    DebuggerNonUser
    -0.51
    oproject
    -0.50
    Superview
    -0.50
    POSITIVE LOGITS
     winning
    3.11
     win
    3.07
     wins
    2.94
     victory
    2.81
     winner
    2.72
     winners
    2.63
    Winning
    2.62
    winning
    2.58
     Winning
    2.55
    win
    2.49
    Activations Density 0.618%

    No Known Activations