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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5955
    Prev
    Next
    INDEX
    Explanations

    references to aesthetic qualities and design elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.52
    Nino
    -0.45
     Nino
    -0.45
     المعيارى
    -0.42
    hamshire
    -0.41
     county
    -0.40
    |_{
    -0.39
    ✤
    -0.38
     Vos
    -0.38
     tight
    -0.37
    POSITIVE LOGITS
     aesthetic
    1.09
    aesthetic
    1.04
     Aesthetic
    1.01
    Aesthetic
    1.00
     cosmetic
    1.00
    cosmetic
    0.97
     aesthetics
    0.97
     estético
    0.94
     Aesthetics
    0.94
     cosmé
    0.93
    Activations Density 0.183%

    No Known Activations