© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3706
    Prev
    Next
    INDEX
    Explanations

    instances of the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XNUMX
    -0.87
     creș
    -0.67
    NUMX
    -0.66
    ]}>
    -0.65
    исленность
    -0.63
     leaſt
    -0.62
     béné
    -0.60
    //}
    -0.60
    What
    -0.59
     Theſe
    -0.59
    POSITIVE LOGITS
     whilst
    1.04
    Tembelea
    0.77
     although
    0.76
     Whilst
    0.75
     perchè
    0.72
     poichè
    0.72
     apabila
    0.71
     optimisation
    0.70
    Whilst
    0.69
     utilising
    0.68
    Activations Density 0.316%

    No Known Activations