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. 14-GEMMASCOPE-RES-16K
    6. 12934
    Prev
    Next
    INDEX
    Explanations

    mentions of art and artistic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.32
     Monfieur
    -1.28
     pleaſure
    -1.20
     ſmall
    -1.15
     ſever
    -1.15
     themſelves
    -1.14
     Diſ
    -1.11
     purpoſe
    -1.10
    ContentAsync
    -1.07
    InSection
    -1.05
    POSITIVE LOGITS
     art
    1.47
     ART
    1.39
     Art
    1.33
     arts
    1.23
    Art
    1.22
    art
    1.17
    ART
    1.14
     Arts
    1.07
     ARTS
    0.97
     arte
    0.94
    Activations Density 0.067%

    No Known Activations