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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6604
    Prev
    Next
    INDEX
    Explanations

    references to sacrificial practices and their significance in culture

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

    Ancient or early peoples/groups

    np_acts-logits-general · gemini-2.0-flash

    ancient peoples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     American
    -0.47
    FieldNumber
    -0.46
    APOLIS
    -0.45
     dollars
    -0.44
     Mr
    -0.43
     Australian
    -0.42
     iceberg
    -0.42
     Park
    -0.42
     
    -0.42
    bonucleic
    -0.41
    POSITIVE LOGITS
     centuries
    0.75
     nomadic
    0.72
     древ
    0.72
     earliest
    0.72
     sedentary
    0.71
     enslaved
    0.71
     warlike
    0.71
     medieval
    0.69
    fromnode
    0.68
     protoimpl
    0.68
    Activations Density 0.701%

    No Known Activations