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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16197
    Prev
    Next
    INDEX
    Explanations

    words related to attractiveness and the act of attracting attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "attract" or "attractive"

    np_acts-logits-general · gemini-2.0-flash

    attract or be attractive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    
    -0.56
    endregion
    -0.49
    SuppressLint
    -0.47
    ništ
    -0.46
    хьтан
    -0.45
        
    -0.44
     actionMode
    -0.42
     microfiber
    -0.41
    lemény
    -0.40
     unix
    -0.39
    POSITIVE LOGITS
     attraction
    1.17
     Attra
    1.10
    Attra
    1.08
     Attraction
    1.05
     attracts
    1.05
    attraction
    1.03
     attract
    1.03
    attra
    1.01
     attracting
    1.01
     attracted
    1.00
    Activations Density 0.198%

    No Known Activations