© 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. 19-GEMMASCOPE-RES-16K
    11. 5039
    Prev
    Next
    INDEX
    Explanations

    phrases expressing contrast or contradiction

    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
     não
    -0.77
     not
    -0.76
    not
    -0.74
     nicht
    -0.70
     NOT
    -0.68
     tidak
    -0.66
     niet
    -0.65
    Not
    -0.65
     bukan
    -0.64
     pertanto
    -0.63
    POSITIVE LOGITS
     vielmehr
    1.13
    rungsseite
    0.89
    而是
    0.88
     autorytatywna
    0.83
    むしろ
    0.83
     actually
    0.81
     بلکه
    0.77
     sondern
    0.77
     propOrder
    0.73
     downright
    0.71
    Activations Density 0.180%

    No Known Activations