© 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. 3446
    Prev
    Next
    INDEX
    Explanations

    the presence of names, particularly variations of the name "Ste" or related names

    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
     disambiguazione
    -0.85
     ExecuteAsync
    -0.71
     LUMP
    -0.71
    Personendaten
    -0.70
    httphttps
    -0.69
    NonQuery
    -0.69
     initComponents
    -0.68
     PopupWindow
    -0.67
    IUrlHelper
    -0.66
    Slf
    -0.65
    POSITIVE LOGITS
     Ste
    1.11
    Ste
    1.03
     STE
    0.94
     ste
    0.91
     Steele
    0.83
    STE
    0.83
    ste
    0.79
     Steen
    0.76
     Stel
    0.72
     Steam
    0.72
    Activations Density 0.092%

    No Known Activations