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. 0-GEMMASCOPE-RES-16K
    6. 6308
    Prev
    Next
    INDEX
    Explanations

    references to a crowd or gatherings of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.67
     purpoſe
    -0.64
     مشين
    -0.57
    Portály
    -0.56
     регионе
    -0.56
     deported
    -0.56
    VIAF
    -0.56
     Houſe
    -0.56
     pleaſure
    -0.55
     상세
    -0.54
    POSITIVE LOGITS
     crowds
    1.61
    crow
    1.34
    Crow
    1.23
     Crow
    1.22
     crowd
    1.21
     CROW
    1.20
     crowding
    1.13
     crowded
    1.06
     Crowd
    1.05
    crowd
    1.03
    Activations Density 0.083%

    No Known Activations