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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15149
    Prev
    Next
    INDEX
    Explanations

    actions related to the physical manipulation or control of objects, particularly involving tape or tapping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lowry
    -0.86
     Marquez
    -0.75
     Cline
    -0.74
     Friedman
    -0.73
    ADVERTISEMENT
    -0.72
     pros
    -0.68
     Lawson
    -0.68
    &&&&
    -0.67
     Schlegel
    -0.66
     Pros
    -0.65
    POSITIVE LOGITS
     TAP
    1.47
     tap
    1.39
     Tape
    1.37
     taps
    1.36
     Tap
    1.35
    Tap
    1.34
    Ta
    1.32
    taps
    1.32
     taping
    1.30
     tapes
    1.30
    Activations Density 0.089%

    No Known Activations