© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7265
    Prev
    Next
    INDEX
    Explanations

    photographic actions and related expressions in narratives

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

    Taking or posing for photos

    np_acts-logits-general · gemini-2.0-flash

    taking photos and selfies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     ujednoznacz
    -0.70
    ThroughAttribute
    -0.64
    DockStyle
    -0.63
    الحياه
    -0.62
    ContentLoaded
    -0.56
    HomeAsUpEnabled
    -0.54
     Commentaires
    -0.54
    tagext
    -0.53
     ویکی‌پدیا
    -0.53
     insuffisamment
    -0.52
    POSITIVE LOGITS
     selfie
    1.14
     shot
    1.12
     selfies
    1.11
     pose
    1.08
     posed
    1.07
     poses
    1.05
     posing
    1.04
     photo
    1.01
     shots
    1.00
     snapshot
    0.98
    Activations Density 0.156%

    No Known Activations