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. 12-GEMMASCOPE-RES-16K
    6. 12952
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal processes and disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.91
     alſo
    -0.90
    BeginContext
    -0.87
     ویکی‌پدیای
    -0.87
     myſelf
    -0.86
     purpoſe
    -0.86
     pleaſure
    -0.83
     neceff
    -0.82
     Jefus
    -0.82
     itſelf
    -0.81
    POSITIVE LOGITS
     Pe
    0.55
     “
    0.53
     Re
    0.53
     Mo
    0.51
    omu
    0.51
    ளி
    0.50
     Se
    0.49
     Tri
    0.49
    parseLong
    0.48
     e
    0.48
    Activations Density 1.041%

    No Known Activations