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. 14207
    Prev
    Next
    INDEX
    Explanations

    issues related to child legitimacy and parental rights

    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
    ISupport
    -0.56
    visionnement
    -0.53
    szám
    -0.46
    ваемые
    -0.46
    dafx
    -0.46
    astă
    -0.45
    ätigkeit
    -0.45
     Toussaint
    -0.42
    retmen
    -0.41
     impati
    -0.41
    POSITIVE LOGITS
     marriage
    2.66
     married
    2.50
     marry
    2.38
    marriage
    2.27
     Marriage
    2.23
     marriages
    2.23
     marrying
    2.21
    Marriage
    2.15
    married
    2.12
     marries
    2.11
    Activations Density 0.525%

    No Known Activations