© 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. 2-GEMMASCOPE-RES-16K
    11. 15326
    Prev
    Next
    INDEX
    Explanations

    instances of the word "perfectly" to indicate a strong emphasis on completion or accuracy

    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
    بوابة
    -0.58
    er
    -0.51
     Similar
    -0.51
     Aids
    -0.50
    SOR
    -0.49
    ••••
    -0.49
    ↵↵↵
    -0.48
    Similar
    -0.47
     hä
    -0.47
    alert
    -0.47
    POSITIVE LOGITS
     perfectly
    2.54
    perfectly
    2.33
     Perfectly
    2.23
    Perfectly
    2.17
     parfaitement
    1.75
     perfectamente
    1.74
     perfeitamente
    1.70
     perfettamente
    1.68
     beautifully
    1.56
     nicely
    1.51
    Activations Density 0.082%

    No Known Activations