© 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. 14203
    Prev
    Next
    INDEX
    Explanations

    elements related to width specifications in a document

    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
    :\/\/
    -0.73
     Gurney
    -0.71
    writeObject
    -0.69
     pelle
    -0.69
    [@"
    -0.68
     app
    -0.64
     HasFactory
    -0.63
     chng
    -0.62
    леп
    -0.61
    App
    -0.61
    POSITIVE LOGITS
    width
    1.61
     width
    1.60
    WIDTH
    1.43
     Width
    1.37
     WIDTH
    1.36
    Width
    1.36
     widths
    1.34
     maxWidth
    1.06
    widths
    1.06
    getWidth
    1.04
    Activations Density 0.049%

    No Known Activations