© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7117
    Prev
    Next
    INDEX
    Explanations

    references to "Sky" in various contexts, including phrases related to skies and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desee
    -0.44
     doors
    -0.42
     recibirá
    -0.41
     regresó
    -0.39
     Substanz
    -0.39
     saiba
    -0.38
     vivía
    -0.38
     braccia
    -0.38
     regresa
    -0.38
    RegressionTest
    -0.38
    POSITIVE LOGITS
    :✨
    0.75
    contentLoaded
    0.73
    expandindo
    0.71
     estekak
    0.69
     ویکی‌پدی
    0.68
     nest
    0.64
    IndentedString
    0.63
    RUnlock
    0.62
     مشين
    0.58
     induction
    0.58
    Activations Density 0.290%

    No Known Activations