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. 15-GEMMASCOPE-RES-16K
    6. 12564
    Prev
    Next
    INDEX
    Explanations

    details related to characteristics and properties of materials in scientific contexts

    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
    onAttach
    -0.62
    posedge
    -0.61
    wpi
    -0.57
    exitRule
    -0.54
    routeProvider
    -0.50
    addCriterion
    -0.48
     $('<
    -0.48
    argmin
    -0.48
    tralight
    -0.47
     Wakil
    -0.45
    POSITIVE LOGITS
     size
    0.70
     ویکی‌پدیا
    0.65
    AccessorTable
    0.64
     shape
    0.63
     frequency
    0.61
     variety
    0.59
     dimension
    0.58
     length
    0.57
     quantity
    0.57
     dimen
    0.57
    Activations Density 0.703%

    No Known Activations