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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 6776
    Prev
    Next
    INDEX
    Explanations

    references to celestial objects and astronomical discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContainerState
    -0.52
     simplifié
    -0.52
    yip
    -0.50
    opolis
    -0.43
     Raven
    -0.42
    DateTimeField
    -0.42
     zenith
    -0.42
     AssemblyProduct
    -0.41
     layui
    -0.41
    avits
    -0.40
    POSITIVE LOGITS
    يكب
    0.75
     Discovered
    0.69
     découver
    0.69
     Италијани
    0.67
    ">//
    0.63
     Siding
    0.63
     asteroid
    0.63
    webElementXpaths
    0.62
    oredCriteria
    0.61
    ArrowToggle
    0.60
    Activations Density 0.119%

    No Known Activations