© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3125
    Prev
    Next
    INDEX
    Explanations

    references to performances and entertainment acts, particularly formal or organized events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    circus tricks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.69
    AndEndTag
    -0.66
    GraphicsUnit
    -0.55
    PYX
    -0.53
     plainte
    -0.53
    ">:
    -0.51
    GenerationType
    -0.50
    omości
    -0.49
     Rohing
    -0.49
     eorum
    -0.49
    POSITIVE LOGITS
     circus
    1.15
     tricks
    1.09
     Circus
    1.08
     trick
    1.01
     magician
    0.99
    circus
    0.96
     Cirque
    0.95
     Tricks
    0.94
    Circus
    0.93
     acrobat
    0.91
    Activations Density 0.138%

    No Known Activations