© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 345
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS syntax elements related to styling and layout properties

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

    after "color"

    np_acts-logits-general · gemini-2.0-flash

    fur quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colors
    -0.97
     Colors
    -0.86
     colours
    -0.86
    Color
    -0.84
    colors
    -0.84
     color
    -0.84
     Color
    -0.83
     Colours
    -0.83
     colored
    -0.79
    Colors
    -0.77
    POSITIVE LOGITS
     AssemblyTitle
    0.76
    ніципа
    0.73
     téléchargez
    0.68
    EnableWeb
    0.66
     ddelweddau
    0.66
     nawr
    0.64
    Tembelea
    0.64
    يميديا
    0.63
     мәкал
    0.62
    hound
    0.62
    Activations Density 0.123%

    No Known Activations