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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 8643
    Prev
    Next
    INDEX
    Explanations

    references to Asian countries and their economic development or improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.81
    extAlignment
    -0.79
    msgTypes
    -0.79
     <=",
    -0.71
    Personendaten
    -0.66
     AssemblyCulture
    -0.66
     تضيفلها
    -0.63
     JAXBElement
    -0.62
     خارجية
    -0.59
     propOrder
    -0.59
    POSITIVE LOGITS
     developing
    0.53
    kmäler
    0.52
    viewDidLoad
    0.52
     emerging
    0.51
     rapidly
    0.50
     development
    0.50
    classpath
    0.48
     Emerging
    0.48
     economies
    0.48
     develop
    0.47
    Activations Density 0.172%

    No Known Activations