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. 23-GEMMASCOPE-RES-16K
    6. 5441
    Prev
    Next
    INDEX
    Explanations

    activities related to leisure and recreation, particularly those involving water and dancing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.67
    DockStyle
    -0.65
    Välislingid
    -0.64
    INCREF
    -0.61
    writeFieldEnd
    -0.61
    ParallelGroup
    -0.60
    ContentAsync
    -0.59
    Datuak
    -0.57
    èvres
    -0.53
    ypeł
    -0.53
    POSITIVE LOGITS
     lessons
    0.84
     expeditions
    0.74
     sessions
    0.73
     clubs
    0.71
     trips
    0.70
     enthusiasts
    0.70
     competitions
    0.69
     excursions
    0.68
     enthusiast
    0.65
     Lessons
    0.65
    Activations Density 0.230%

    No Known Activations