© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 6266
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to graphs and combinatorial structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.87
    setVerticalGroup
    -0.71
    ViewFeatures
    -0.69
    MigrationBuilder
    -0.69
    يكب
    -0.67
     estekak
    -0.67
     متعلقه
    -0.65
    SpringBootTest
    -0.65
     ExecuteAsync
    -0.65
     समीक्षाओं
    -0.61
    POSITIVE LOGITS
     dozen
    0.82
     number
    0.70
     amount
    0.64
    dozen
    0.58
    عدد
    0.57
     dozens
    0.57
     more
    0.56
     million
    0.55
     maxn
    0.53
     numerous
    0.53
    Activations Density 1.253%

    No Known Activations