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. 1-GEMMASCOPE-RES-16K
    6. 9302
    Prev
    Next
    INDEX
    Explanations

    references to places, names, and notable entities in a political or social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...
    -0.55
     Maior
    -0.54
    a
    -0.53
     minutter
    -0.50
    Ma
    -0.49
     خصوصی
    -0.47
    ธ์
    -0.47
    k
    -0.47
    便是
    -0.46
    sträger
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.90
     Wikimedijinoj
    0.86
    SequentialGroup
    0.84
    tvguidetime
    0.82
    rrggbb
    0.80
     архивлан
    0.78
    Revenir
    0.78
    webElement
    0.75
    
    0.75
    GEBURTSDATUM
    0.74
    Activations Density 0.864%

    No Known Activations