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. 3-GEMMASCOPE-RES-16K
    6. 12819
    Prev
    Next
    INDEX
    Explanations

    references to Sri Lanka or related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -1.01
    AppMethodBeat
    -0.92
     '\\;'
    -0.91
    hej
    -0.87
    URLException
    -0.86
     desem
    -0.85
    Rhestr
    -0.84
     Marcell
    -0.84
     calendriers
    -0.83
     Tamp
    -0.82
    POSITIVE LOGITS
     Sri
    1.55
    Sri
    1.30
     sri
    0.95
     Lanka
    0.84
    sri
    0.81
     Thi
    0.73
     Nic
    0.73
     SRI
    0.68
     Fame
    0.68
     Lankan
    0.66
    Activations Density 0.115%

    No Known Activations