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. 11-GEMMASCOPE-RES-16K
    6. 13682
    Prev
    Next
    INDEX
    Explanations

    references to personnel and staff in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEncoder
    -0.94
     XCTest
    -0.86
     Tric
    -0.86
     Rien
    -0.85
     Zol
    -0.83
    Rien
    -0.81
     kilometre
    -0.78
     Chol
    -0.77
     conquerors
    -0.77
     Nazar
    -0.76
    POSITIVE LOGITS
     staff
    1.67
     Staff
    1.46
     staffs
    1.44
    Staff
    1.41
    staff
    1.35
     STAFF
    1.33
    STAFF
    1.21
     staffing
    0.91
     staffers
    0.91
     Staffel
    0.86
    Activations Density 0.030%

    No Known Activations