© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 8987
    Prev
    Next
    INDEX
    Explanations

    references to the concept of appeal or attraction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuppressLint
    -0.35
    rungsseite
    -0.34
    Voci
    -0.34
    Становништво
    -0.34
    
    -0.32
    Шаг
    -0.31
    AsUp
    -0.29
    addContainerGap
    -0.29
    initData
    -0.28
     initData
    -0.28
    POSITIVE LOGITS
     attraction
    1.07
     Attraction
    1.00
    Attra
    0.97
    attraction
    0.97
     attractiveness
    0.92
     Attra
    0.91
     attractions
    0.91
    attra
    0.89
     atracción
    0.85
     attract
    0.84
    Activations Density 0.227%

    No Known Activations