© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10519
    Prev
    Next
    INDEX
    Explanations

    references to specific tattoo designs, particularly crosses

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

    Tattoos, especially crosses

    np_acts-logits-general · gemini-2.0-flash

    tattoo crosses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XDECREF
    -0.73
     SwiftUI
    -0.68
     ब्रेकडाउन
    -0.63
    ModelAdmin
    -0.62
    +#+
    -0.57
     binoculars
    -0.56
    Sortie
    -0.56
     noqa
    -0.56
     webinars
    -0.54
    füh
    -0.53
    POSITIVE LOGITS
     tattoo
    1.40
     tattoos
    1.27
     Tattoo
    1.17
     tattooed
    1.10
     inked
    1.10
     Tattoos
    1.08
     ink
    1.06
    Tattoo
    1.05
    tattoo
    1.04
     tats
    1.04
    Activations Density 0.083%

    No Known Activations