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. 21-GEMMASCOPE-RES-16K
    6. 7431
    Prev
    Next
    INDEX
    Explanations

    references to spending time with family

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tières
    -0.49
    KURZBESCHREIBUNG
    -0.46
     conto
    -0.44
     azon
    -0.44
    ynia
    -0.44
    っこう
    -0.44
    aş
    -0.43
    zarchiwizowane
    -0.43
    DataStore
    -0.43
    phic
    -0.43
    POSITIVE LOGITS
     spending
    1.54
    Spending
    1.52
     Spending
    1.49
     spend
    1.47
     Spend
    1.38
    Spend
    1.33
     spends
    1.31
    spending
    1.28
    spend
    1.25
     spent
    1.15
    Activations Density 0.158%

    No Known Activations