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. 17-GEMMASCOPE-RES-16K
    6. 6095
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the act of painting and artistic expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fré
    -0.54
    각주
    -0.53
    XmlRootElement
    -0.52
     Arque
    -0.51
    PathParam
    -0.51
    #}
    -0.50
    segue
    -0.49
    ↩
    -0.48
    Fré
    -0.48
    ArgsConstructor
    -0.48
    POSITIVE LOGITS
     paint
    1.85
     painting
    1.79
     Paint
    1.73
     paints
    1.72
     PAINT
    1.66
     painted
    1.64
    paint
    1.63
     Painting
    1.63
    Paint
    1.61
     Paints
    1.60
    Activations Density 0.166%

    No Known Activations