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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 11647
    Prev
    Next
    INDEX
    Explanations

    events and gatherings involving large groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currently
    -0.68
     attualmente
    -0.61
    currently
    -0.58
     bislang
    -0.58
    redux
    -0.57
    forChild
    -0.57
     ممکن
    -0.57
     presently
    -0.56
     momentan
    -0.56
    glMatrixMode
    -0.55
    POSITIVE LOGITS
     attendees
    0.98
     enjoyed
    0.90
    Afterwards
    0.82
     participants
    0.81
     attendee
    0.80
    Attendees
    0.80
     Afterwards
    0.79
     thanked
    0.77
     turnout
    0.74
     estuvo
    0.73
    Activations Density 0.261%

    No Known Activations