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. 5-GEMMASCOPE-RES-16K
    6. 4558
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Pa" and related variants in a programming or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.86
    {{\
    -0.74
     reger
    -0.72
     Holtz
    -0.65
    {"
    -0.65
    ✨✨
    -0.65
     Aldrich
    -0.64
     comun
    -0.63
     pican
    -0.62
     CET
    -0.62
    POSITIVE LOGITS
     Pa
    2.13
     pa
    1.96
    Pa
    1.88
     PA
    1.80
    pa
    1.67
    PA
    1.57
     Paxton
    1.30
     Paine
    1.22
     Paredes
    1.17
     Pas
    1.12
    Activations Density 0.095%

    No Known Activations