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-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1838
    Prev
    Next
    INDEX
    Explanations

    references to tattoos, particularly gothic and cross designs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.46
     Arag
    -0.40
     Signalez
    -0.38
    thâu
    -0.38
    🧺
    -0.37
     duduk
    -0.37
     họp
    -0.37
    Népesség
    -0.36
    ISupport
    -0.36
     Nino
    -0.36
    POSITIVE LOGITS
     tattoo
    1.15
     tattoos
    1.09
     tattooed
    1.00
     Tattoo
    0.99
    tattoo
    0.96
    Tattoo
    0.94
     tatuagem
    0.92
     Tattoos
    0.91
     tatu
    0.85
     tatuaje
    0.83
    Activations Density 0.184%

    No Known Activations