© 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. 16116
    Prev
    Next
    INDEX
    Explanations

    punctuation and other non-alphabetic characters

    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
     sometimes
    -0.70
     but
    -0.70
     BUT
    -0.65
    anmoins
    -0.60
    Sometimes
    -0.60
    but
    -0.60
     parfois
    -0.59
    sometimes
    -0.59
     Sometimes
    -0.59
    maar
    -0.59
    POSITIVE LOGITS
    Commenting
    1.18
     commented
    0.92
     commenting
    0.85
    Said
    0.81
    Према
    0.77
    “
    0.75
    said
    0.73
    Says
    0.72
     congratulated
    0.72
     “
    0.71
    Activations Density 0.109%

    No Known Activations