© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6872
    Prev
    Next
    INDEX
    Explanations

    text related to colors and descriptions associated with clothing and appearances

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

    colors, hues, or shades

    np_acts-logits-general · gemini-2.0-flash

    color and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.81
    MessageTagHelper
    -0.77
    makeConstraints
    -0.77
     EconPapers
    -0.76
    BeginInit
    -0.76
    StoryboardSegue
    -0.74
    ConstraintMaker
    -0.74
    UnsafeEnabled
    -0.72
    AndroidJUnit
    -0.71
    Personensuche
    -0.71
    POSITIVE LOGITS
     color
    0.54
    yves
    0.50
    Capítulo
    0.49
     hue
    0.49
    ########.
    0.48
     colour
    0.48
    cvtColor
    0.48
    Reflect
    0.46
    setTextColor
    0.46
     hues
    0.44
    Activations Density 0.341%

    No Known Activations