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. 9-GEMMASCOPE-RES-16K
    6. 9212
    Prev
    Next
    INDEX
    Explanations

    mentions of artists and their works in an art context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnitTesting
    -0.73
     consultato
    -0.73
    posedge
    -0.66
     MainAxisSize
    -0.65
     ویکی‌پدیای
    -0.64
    GIVEREF
    -0.63
    endpush
    -0.63
    HomeAsUpEnabled
    -0.62
     deviceId
    -0.62
    arrêter
    -0.61
    POSITIVE LOGITS
     paintings
    0.86
     painting
    0.84
     painters
    0.73
     painter
    0.71
     artist
    0.65
     artists
    0.64
     artwork
    0.61
     Paintings
    0.59
     art
    0.59
     obrazy
    0.58
    Activations Density 0.127%

    No Known Activations