Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 12132
    Prev
    Next
    INDEX
    Explanations

    terms related to crowds and gathering events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.54
    mtd
    -0.51
     conci
    -0.51
     integ
    -0.49
    Détails
    -0.49
    aroa
    -0.49
     propOrder
    -0.48
    cales
    -0.48
     intercal
    -0.46
    IndentedString
    -0.46
    POSITIVE LOGITS
     crowd
    1.32
     crowds
    1.28
    crowd
    1.17
     Crowd
    1.09
     crowded
    1.08
     crowding
    1.07
    Crowd
    1.07
     throng
    1.03
    crow
    0.94
     tł
    0.90
    Activations Density 0.292%

    No Known Activations