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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 13495
    Prev
    Next
    INDEX
    Explanations

    references to financial or organizational activities related to biomedical or charity sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.97
    webElementXpaths
    -0.85
    sizeCache
    -0.84
     дописавши
    -0.83
    SourceChecksum
    -0.78
    XmlAccessType
    -0.76
    parsedMessage
    -0.75
    BeginInit
    -0.75
     kaarangay
    -0.74
    цездатний
    -0.73
    POSITIVE LOGITS
    bila
    0.57
    Instrumented
    0.47
     (“
    0.47
    tig
    0.43
    Архівовано
    0.43
    त्रा
    0.42
     ("
    0.41
     hujan
    0.41
    $--
    0.41
    ädie
    0.40
    Activations Density 0.660%

    No Known Activations