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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 857
    Prev
    Next
    INDEX
    Explanations

    descriptions and actions related to painting and home improvement tasks

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

    painting, colors, or metallic materials

    np_acts-logits-general · gemini-2.0-flash

    paint, painted, painting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.75
    AddTagHelper
    -0.69
     kasarigan
    -0.69
     ligiloj
    -0.62
     بيها
    -0.61
    bole
    -0.61
    IConfiguration
    -0.59
     ब्रेकडाउन
    -0.58
    mybatisplus
    -0.56
     activado
    -0.56
    POSITIVE LOGITS
     paint
    1.90
     Paint
    1.70
     painting
    1.67
    paint
    1.56
     painted
    1.56
    Paint
    1.55
     PAINT
    1.54
     Painting
    1.52
    PAINT
    1.50
    painting
    1.46
    Activations Density 0.091%

    No Known Activations