© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 719
    Prev
    Next
    INDEX
    Explanations

    elements related to photography and photoshoots

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    photography or portraits

    np_acts-logits-general · gemini-2.0-flash

    posed portraits and photography sessions

    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
    Negative Logits
    Lähteet
    -0.34
     pauvreté
    -0.30
     coloris
    -0.30
     ESL
    -0.30
     Arabic
    -0.29
     CTV
    -0.29
     English
    -0.28
     verfolgen
    -0.28
    ActivityCompat
    -0.28
    createStatement
    -0.27
    POSITIVE LOGITS
     disambiguazione
    0.73
    IBOutlet
    0.68
     photoshoot
    0.66
     myſelf
    0.65
    +#+#
    0.65
     poses
    0.61
     posed
    0.60
    photographer
    0.60
     selfie
    0.60
     portrait
    0.60
    Activations Density 0.124%

    No Known Activations