© 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. 19-GEMMASCOPE-RES-16K
    11. 15493
    Prev
    Next
    INDEX
    Explanations

    elements related to noteworthy projects, innovations, or significant structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -1.00
    ImageContext
    -0.74
    +#+#
    -0.74
    таратура
    -0.72
     Chwiliwch
    -0.69
     onCancelled
    -0.68
     CreateTagHelper
    -0.66
    StoryboardSegue
    -0.66
    Tembelea
    -0.63
    ագրություններ
    -0.61
    POSITIVE LOGITS
     multi
    0.98
     five
    0.80
     four
    0.80
    multi
    0.77
     eight
    0.77
     multifaceted
    0.77
     six
    0.75
     highly
    0.74
     heavily
    0.74
     large
    0.74
    Activations Density 0.463%

    No Known Activations