© 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. 2-GEMMASCOPE-RES-16K
    11. 8464
    Prev
    Next
    INDEX
    Explanations

    instances of humor, specifically the use of "lol" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.54
     el
    -0.50
      
    -0.49
    .
    -0.48
    el
    -0.47
     One
    -0.46
     one
    -0.45
    permum
    -0.45
    чук
    -0.45
     El
    -0.44
    POSITIVE LOGITS
     للمعارف
    1.03
     للاسماء
    1.00
    ]--;
    0.99
     ujednoznacz
    0.94
     LOL
    0.92
     Lol
    0.91
     lol
    0.90
    InputTagHelper
    0.87
     Allociné
    0.87
     calendriers
    0.87
    Activations Density 0.019%

    No Known Activations