© 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. 15472
    Prev
    Next
    INDEX
    Explanations

    occurrences of non-breaking space characters or similar formatting elements

    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
     africain
    -0.62
    ouder
    -0.62
    ähig
    -0.61
     penyel
    -0.61
    /*
    -0.60
     sonno
    -0.59
     textStatus
    -0.59
     całej
    -0.58
    ::_('
    -0.57
    writeHead
    -0.56
    POSITIVE LOGITS
    nbsp
    1.17
    Â
    0.79
     Â
    0.70
     Ã
    0.68
    illingham
    0.67
     semester
    0.66
     &#
    0.64
    GT
    0.63
     AssemblyVersion
    0.62
     ·
    0.62
    Activations Density 0.086%

    No Known Activations