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. 13-GEMMASCOPE-RES-16K
    6. 137
    Prev
    Next
    INDEX
    Explanations

    references to children and family activities

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

    activities, items, and events related to children and family entertainment.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FileReader
    -0.49
     فريبيس
    -0.48
     numerus
    -0.45
    RTLI
    -0.45
     démarche
    -0.43
    rayage
    -0.43
     cuadro
    -0.41
     CHORUS
    -0.41
     mxArray
    -0.41
     Exactos
    -0.40
    POSITIVE LOGITS
     amusements
    0.94
     entertainment
    0.91
     entertain
    0.88
     kids
    0.87
     pleaſure
    0.84
     entertainments
    0.84
     enjoyment
    0.84
     excitement
    0.82
     amusement
    0.80
     interactive
    0.78
    Activations Density 0.219%

    No Known Activations