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. 6-GEMMASCOPE-RES-16K
    6. 2554
    Prev
    Next
    INDEX
    Explanations

    critical moments in competitive sports events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    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
    -0.65
     '\\;'
    -0.62
     تانيه
    -0.57
     depositphotos
    -0.56
    Rhestr
    -0.55
     فريبيس
    -0.55
     Henk
    -0.54
    vento
    -0.54
     ***!
    -0.53
    出版年
    -0.52
    POSITIVE LOGITS
    setViewportView
    0.59
     ExecuteAsync
    0.59
    IsPostBack
    0.57
    ReusableCell
    0.56
    SharedDtor
    0.56
     >=",
    0.55
    LabelTagHelper
    0.55
    MessageState
    0.54
    értelmű
    0.54
     propOrder
    0.53
    Activations Density 0.131%

    No Known Activations