© 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. 21-GEMMASCOPE-RES-16K
    11. 3665
    Prev
    Next
    INDEX
    Explanations

    elements related to colors and visual attributes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     htons
    -0.50
    forChild
    -0.43
    nodoc
    -0.42
     betrug
    -0.42
    addPreferredGap
    -0.42
    Bread
    -0.41
     Bread
    -0.41
     seismo
    -0.40
     Söz
    -0.40
    dades
    -0.40
    POSITIVE LOGITS
     color
    2.14
     blue
    2.05
     colors
    1.99
     colour
    1.96
     yellow
    1.96
     purple
    1.90
     colored
    1.89
     green
    1.86
     colours
    1.84
     pink
    1.82
    Activations Density 1.103%

    No Known Activations