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. 20-GEMMASCOPE-RES-16K
    6. 16073
    Prev
    Next
    INDEX
    Explanations

    database query parameters and sorting specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.82
    HandlerContext
    -0.52
    awtextra
    -0.52
     Vigil
    -0.50
    siasme
    -0.50
     devin
    -0.49
     vš
    -0.49
    BeginContext
    -0.49
    ništvo
    -0.49
     esternos
    -0.48
    POSITIVE LOGITS
     sorting
    1.28
    Sort
    1.27
     Sort
    1.25
     Sorting
    1.25
     sorted
    1.22
    sort
    1.21
     SORT
    1.21
    SORT
    1.20
    Sorting
    1.18
    排序
    1.15
    Activations Density 0.230%

    No Known Activations