© 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. 14-GEMMASCOPE-RES-16K
    11. 2468
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions, particularly the word "and," indicating connections or lists within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.54
     itſelf
    -1.54
     himſelf
    -1.39
     myſelf
    -1.37
     Jefus
    -1.36
    ſelf
    -1.29
     houſe
    -1.29
     Majefty
    -1.27
     poffible
    -1.26
     purpoſe
    -1.24
    POSITIVE LOGITS
    /
    1.00
     and
    0.91
     và
    0.89
     And
    0.89
     AND
    0.87
     the
    0.82
     och
    0.80
     a
    0.79
     then
    0.78
     и
    0.78
    Activations Density 1.396%

    No Known Activations