© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9586
    Prev
    Next
    INDEX
    Explanations

    descriptions related to beauty and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kring
    -0.47
     casse
    -0.45
     Mancha
    -0.44
    kring
    -0.43
     requestCode
    -0.43
    InBytes
    -0.43
    がら
    -0.42
    îné
    -0.42
    nissen
    -0.42
    jména
    -0.42
    POSITIVE LOGITS
     Beautiful
    0.90
    Beautiful
    0.89
    beautiful
    0.84
     BEAUTIFUL
    0.84
     beautiful
    0.83
    Beauty
    0.82
     Beauty
    0.82
     beauty
    0.81
    beauty
    0.78
     pięk
    0.77
    Activations Density 0.039%

    No Known Activations