© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14865
    Prev
    Next
    INDEX
    Explanations

    mentions of physical attraction and relationships

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

    attractiveness or sexual appeal

    np_acts-logits-general · gemini-2.0-flash

    attractiveness and quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.94
    setVerticalGroup
    -0.91
     >=",
    -0.90
    UserScript
    -0.82
     propOrder
    -0.77
    évaluateur
    -0.77
     CreateTagHelper
    -0.76
    errHandler
    -0.73
    DrawerToggle
    -0.73
     Roskov
    -0.72
    POSITIVE LOGITS
     sexy
    1.17
     attractive
    1.15
     sex
    1.12
     sexual
    1.10
     handsome
    1.09
     dating
    1.07
     sexually
    1.04
    Attra
    1.00
     flirt
    1.00
     attractiveness
    0.96
    Activations Density 0.371%

    No Known Activations