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. 5-GEMMASCOPE-RES-16K
    6. 703
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to devices and circuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.63
     EconPapers
    -0.59
     malah
    -0.54
     MainAxisSize
    -0.53
    modern
    -0.53
    mergeFrom
    -0.51
    move
    -0.51
     seemingly
    -0.50
     Anything
    -0.49
    kok
    -0.49
    POSITIVE LOGITS
    dirond
    0.64
    findpost
    0.62
    VIAF
    0.62
     AppBundle
    0.61
     الرياضيه
    0.60
     AssemblyProduct
    0.60
    исленность
    0.60
    MessageTagHelper
    0.59
     pylint
    0.59
    queryInterface
    0.59
    Activations Density 1.413%

    No Known Activations