Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 21
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terminology relating to data analysis and biological factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical expressions or notation.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.07
    principalTable
    -0.84
     ExecuteAsync
    -0.80
    rrggbb
    -0.80
    GEBURTSDATUM
    -0.79
    webElementXpaths
    -0.79
    invokeLater
    -0.77
    RenderAtEndOf
    -0.75
    MessageTagHelper
    -0.73
     referenties
    -0.72
    POSITIVE LOGITS
     INDUSTRIES
    0.43
     Industries
    0.42
    خره
    0.41
     mass
    0.40
    슷
    0.39
     مذه
    0.39
    gang
    0.38
     double
    0.38
    katkan
    0.38
    цем
    0.38
    Activations Density 0.967%

    No Known Activations