© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 11804
    Prev
    Next
    INDEX
    Explanations

    the term "picture" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    EndGlobalSection
    -0.64
    Demografía
    -0.63
    MLLoader
    -0.62
    UserScript
    -0.60
    ГЛА
    -0.59
    ClientRect
    -0.58
    γη
    -0.57
    timmt
    -0.57
    IGENCE
    -0.56
     żel
    -0.56
    POSITIVE LOGITS
     picture
    2.44
    picture
    2.36
     Picture
    2.27
    Picture
    2.17
     pictures
    1.97
     PICTURE
    1.94
    PICTURE
    1.88
    pictures
    1.77
     Pictures
    1.73
    Pictures
    1.71
    Activations Density 0.039%

    No Known Activations