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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 11172
    Prev
    Next
    INDEX
    Explanations

    references to stylesheets and the term "Eclipse."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.87
    ьаж
    -0.68
    UnknownFields
    -0.65
    minecraft
    -0.64
    #
    -0.60
     Quelles
    -0.55
     nakalista
    -0.54
    Vaya
    -0.54
    RatingBar
    -0.53
     kary
    -0.53
    POSITIVE LOGITS
    eclipse
    1.97
    AnchorStyles
    1.12
    stylesheet
    0.85
    CodeAnalysis
    0.81
    @[
    0.75
     eclipse
    0.74
    googleapis
    0.74
    tvguidetime
    0.72
     تضيفلها
    0.72
    jetbrains
    0.71
    Activations Density 0.011%

    No Known Activations