© 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. 1-GEMMASCOPE-RES-16K
    11. 6592
    Prev
    Next
    INDEX
    Explanations

    references to the city of Paris

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.59
    zmán
    -0.57
     suppression
    -0.56
    Datuak
    -0.55
    </tfoot>
    -0.53
    ?,?,
    -0.52
    transpiration
    -0.52
    raisemb
    -0.52
    ̍t
    -0.52
     Suppression
    -0.51
    POSITIVE LOGITS
    ImageContext
    0.90
    Hentet
    0.75
    mybatisplus
    0.73
    PreferredItem
    0.71
    AndEndTag
    0.68
     CreateTagHelper
    0.67
     defaultstate
    0.67
     *__
    0.62
     Syndrome
    0.61
    BeginContext
    0.61
    Activations Density 0.098%

    No Known Activations