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. 23-GEMMASCOPE-RES-16K
    6. 12020
    Prev
    Next
    INDEX
    Explanations

    references to international meetings or summits involving key geopolitical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.57
    tagHelperRunner
    -0.52
    CodeAnalysis
    -0.51
    ndale
    -0.49
    DataPropertyName
    -0.48
    gnac
    -0.47
    phanumeric
    -0.47
    mployed
    -0.47
    وقات
    -0.47
    colorbar
    -0.47
    POSITIVE LOGITS
     summit
    1.07
     Summit
    0.96
    summit
    0.89
    Summit
    0.87
     sommet
    0.86
     summits
    0.85
     conference
    0.80
     ministerial
    0.79
     cumbre
    0.78
     delegates
    0.76
    Activations Density 0.110%

    No Known Activations