© 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. 21-GEMMASCOPE-RES-16K
    11. 15888
    Prev
    Next
    INDEX
    Explanations

    elements of irony and humor in descriptions

    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
     "..\..\..\
    -0.78
     estekak
    -0.76
     "..\..\
    -0.76
     bowiem
    -0.70
     nämlich
    -0.67
     ddelweddau
    -0.66
    一是
    -0.63
     firstly
    -0.62
    either
    -0.61
     firft
    -0.61
    POSITIVE LOGITS
     all
    1.71
     allemaal
    1.61
     tudo
    1.51
     semuanya
    1.40
    all
    1.38
    这一切
    1.29
     etc
    1.23
     semua
    1.23
    すべて
    1.21
    Bref
    1.20
    Activations Density 0.309%

    No Known Activations