© 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. 10-GEMMASCOPE-RES-16K
    11. 5650
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section denoted by a specific tag

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LCCN
    -0.82
    WithIOException
    -0.81
    ουσ
    -0.79
    djangoproject
    -0.78
    __':
    -0.74
    setVerticalGroup
    -0.72
    :✨
    -0.71
     ویکی‌پدی
    -0.71
     betweenstory
    -0.70
    олові
    -0.68
    POSITIVE LOGITS
    <blockquote>
    0.67
    <em>
    0.65
    <strong>
    0.63
     sauvages
    0.61
     sèche
    0.55
     vertes
    0.55
     clienti
    0.54
     rangs
    0.54
     pauv
    0.54
     heureux
    0.52
    Activations Density 0.066%

    No Known Activations