Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 12792
    Prev
    Next
    INDEX
    Explanations

    elements related to the artistic process and compositional techniques

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

    Composition, spatial relations, and artistic techniques

    np_acts-logits-general · gemini-2.0-flash

    composition and visual description

    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
     '\\;'
    -0.83
    :✨
    -0.76
    AndEndTag
    -0.71
    Chham
    -0.69
    enumi
    -0.63
     honte
    -0.63
     espé
    -0.63
     تضيفلها
    -0.61
    findpost
    -0.61
     odeur
    -0.61
    POSITIVE LOGITS
     compositional
    0.91
     composition
    0.81
     compositions
    0.73
     planes
    0.66
    composition
    0.65
     forms
    0.65
     viewer
    0.65
     proportions
    0.64
     Composition
    0.63
     proportion
    0.62
    Activations Density 0.166%

    No Known Activations