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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 8372
    Prev
    Next
    INDEX
    Explanations

    themes related to visual art and artists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.63
     Editors
    -0.53
     diren
    -0.52
    kyo
    -0.52
    agem
    -0.49
    adget
    -0.49
     Architekten
    -0.48
     Слу
    -0.48
    ussch
    -0.47
    ({});
    -0.47
    POSITIVE LOGITS
     work
    1.15
     oeuvre
    0.99
     works
    0.98
     style
    0.98
     creations
    0.93
     œuvre
    0.86
    work
    0.84
     stijl
    0.83
     styles
    0.81
     signature
    0.79
    Activations Density 0.218%

    No Known Activations