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. 6408
    Prev
    Next
    INDEX
    Explanations

    references to luxury items or valuable possessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    kháu
    -0.60
    exitRule
    -0.53
     Duckworth
    -0.52
    PDOException
    -0.52
     ProtoMessage
    -0.50
     peindre
    -0.50
     gynhyrchwyd
    -0.50
    pyplot
    -0.49
    styleType
    -0.48
    ViewFeatures
    -0.48
    POSITIVE LOGITS
     jewelry
    1.53
     jewellery
    1.40
     Jewelry
    1.39
     necklace
    1.34
     jew
    1.31
     necklaces
    1.28
     Jewellery
    1.25
     gold
    1.25
    jewelry
    1.20
     jewel
    1.20
    Activations Density 0.139%

    No Known Activations