© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 29
    Prev
    Next
    INDEX
    Explanations

    descriptions of product features and aesthetic qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.58
    RegressionTest
    -0.57
    +#+#
    -0.57
    apparently
    -0.57
     "..\..\..\
    -0.56
    expensive
    -0.55
     hitherto
    -0.55
    Ayer
    -0.54
     "..\..\
    -0.54
    ногда
    -0.54
    POSITIVE LOGITS
     sturdy
    0.85
     stylish
    0.82
     durable
    0.79
     sleek
    0.77
     beautifully
    0.76
     featuring
    0.73
     Featuring
    0.72
    Featuring
    0.71
     adorable
    0.71
     ideal
    0.70
    Activations Density 0.113%

    No Known Activations