© 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
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6014
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "try" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.38
     lose
    -0.37
     layui
    -0.36
    従
    -0.35
     isInitialized
    -0.35
    ftagPool
    -0.35
     prévu
    -0.34
     فريبيس
    -0.32
    RTSC
    -0.31
     '{@
    -0.31
    POSITIVE LOGITS
     winning
    1.03
     losing
    0.94
    Winning
    0.93
     Winning
    0.93
    winning
    0.93
     Losing
    0.84
    Losing
    0.81
    try
    0.76
     Learning
    0.74
    Learning
    0.74
    Activations Density 0.054%

    No Known Activations