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. 16-GEMMASCOPE-RES-16K
    6. 6589
    Prev
    Next
    INDEX
    Explanations

    references to seasonal cycles and their cultural significance

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

    the distant past

    np_acts-logits-general · gemini-2.0-flash

    ancient or historical things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    قایناق‌لار
    -0.52
     الجديدة
    -0.48
    gar
    -0.48
     espon
    -0.48
     un
    -0.48
    GeneratedCode
    -0.47
    oughlin
    -0.46
     оригіналу
    -0.46
    اند
    -0.46
     '.',
    -0.45
    POSITIVE LOGITS
     ancient
    1.27
     centuries
    1.20
    ancient
    1.20
    Ancient
    1.08
     millennia
    1.07
     Ancient
    1.07
     antiquity
    0.97
     oldest
    0.95
     ancients
    0.94
     historically
    0.94
    Activations Density 0.464%

    No Known Activations