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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 850
    Prev
    Next
    INDEX
    Explanations

    references to popular tourist attractions and landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    places to visit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.58
    脚注の使い方
    -0.55
     مشين
    -0.52
     tarko
    -0.48
     epä
    -0.47
     twij
    -0.46
     ब्रेकडाउन
    -0.46
    LabelTagHelper
    -0.46
    Tikang
    -0.45
    SuspendLayout
    -0.44
    POSITIVE LOGITS
     gardens
    0.58
     shops
    0.49
     cafés
    0.48
     Enjoy
    0.47
     farms
    0.47
     enjoying
    0.47
     panor
    0.47
     nightlife
    0.47
     museums
    0.46
    Enjoying
    0.46
    Activations Density 0.013%

    No Known Activations