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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5374
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.69
     ElementRef
    -0.67
     Balo
    -0.64
    horizontalLayout
    -0.63
     Mahomet
    -0.61
    picasso
    -0.59
     Chriftian
    -0.58
     Anak
    -0.57
    Career
    -0.57
     sibi
    -0.57
    POSITIVE LOGITS
    ://
    2.94
    ://"
    1.67
    :\/\/
    1.19
    :///
    1.13
    ://$
    1.05
    ="//
    1.04
    www
    0.92
    {§
    0.78
    {//
    0.75
    errHandler
    0.75
    Activations Density 0.040%

    No Known Activations