© 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. 3654
    Prev
    Next
    INDEX
    Explanations

    discourse markers and transition phrases in discussions

    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
    ſelf
    -1.01
     myſelf
    -0.97
     Efq
    -0.95
    ſelves
    -0.93
    felves
    -0.90
     poffe
    -0.88
     itſelf
    -0.87
     Monfieur
    -0.87
     uſed
    -0.85
    felf
    -0.83
    POSITIVE LOGITS
     it
    0.88
     he
    0.66
     It
    0.59
     there
    0.55
     they
    0.55
    It
    0.50
     I
    0.50
     their
    0.49
     the
    0.49
     its
    0.49
    Activations Density 0.032%

    No Known Activations