© 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. 0-GEMMASCOPE-RES-16K
    11. 10813
    Prev
    Next
    INDEX
    Explanations

    phrases describing attractiveness or appealing qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sectors
    -0.49
     sector
    -0.49
     council
    -0.46
     unanimously
    -0.44
    CppMethod
    -0.44
     fleet
    -0.42
     Sectors
    -0.42
     correos
    -0.41
     security
    -0.40
     commissioned
    -0.40
    POSITIVE LOGITS
     attractive
    1.03
     attra
    1.03
    Attra
    1.02
    attraction
    0.99
     attraction
    0.99
    attractive
    0.99
     attractiveness
    0.97
     Attractive
    0.93
     Attraction
    0.92
     attract
    0.87
    Activations Density 0.276%

    No Known Activations