© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 7634
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and periods, indicating sentence structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    حياته
    -0.73
    }{*}{}
    -0.68
    Upgrade
    -0.66
    ESTY
    -0.66
    حياتها
    -0.65
     незавершена
    -0.65
    /***/
    -0.64
    waitKey
    -0.62
    FontStyle
    -0.61
    ftagPool
    -0.57
    POSITIVE LOGITS
     larmes
    0.73
     renang
    0.72
     Kaly
    0.70
     skolen
    0.69
    HomeAsUpEnabled
    0.69
     gambe
    0.67
     plads
    0.67
     laurel
    0.66
     sereia
    0.66
     myſelf
    0.65
    Activations Density 0.479%

    No Known Activations