© 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. 8483
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to user interface components in code

    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
    AddTagHelper
    -0.88
    Tembelea
    -0.87
    cshtml
    -0.86
    setVerticalGroup
    -0.83
     дописавши
    -0.76
    +#+#
    -0.75
    twimg
    -0.74
    ValueGeneration
    -0.67
     Biôgrafia
    -0.67
    ViewFeatures
    -0.67
    POSITIVE LOGITS
     Sal
    0.50
    PSO
    0.49
    burg
    0.47
    cules
    0.47
     tabPage
    0.46
    textBox
    0.45
    mother
    0.45
     mother
    0.44
     line
    0.43
    ssal
    0.43
    Activations Density 0.045%

    No Known Activations