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. 23-GEMMASCOPE-RES-16K
    6. 8986
    Prev
    Next
    INDEX
    Explanations

    references to visual art and composition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.78
    ValueGenerated
    -0.73
    AndEndTag
    -0.70
    wikk
    -0.67
    InjectAttribute
    -0.60
     mijne
    -0.59
     honte
    -0.57
    transQ
    -0.57
    новништво
    -0.56
    cimientos
    -0.55
    POSITIVE LOGITS
     painting
    1.08
     painted
    0.94
     portrait
    0.91
     paintings
    0.88
    painting
    0.87
     portraits
    0.84
     depiction
    0.84
     depict
    0.83
     Painting
    0.82
     portray
    0.82
    Activations Density 0.182%

    No Known Activations