© 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. 15068
    Prev
    Next
    INDEX
    Explanations

    different forms of articles and prepositions in various languages

    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
     houſe
    -1.32
     Monfieur
    -1.25
     Chriftian
    -1.24
     itſelf
    -1.23
     purpoſe
    -1.22
     Majefty
    -1.21
     Houſe
    -1.20
     pleaſure
    -1.20
     ſche
    -1.19
     raiſ
    -1.18
    POSITIVE LOGITS
     same
    1.12
     most
    1.03
     last
    0.95
     
    0.92
     “
    0.91
     latter
    0.89
     "
    0.85
     final
    0.84
     entire
    0.84
     new
    0.83
    Activations Density 0.015%

    No Known Activations