© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28418
    Prev
    Next
    INDEX
    Explanations

    references to color or shade

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

    shade and shaded things

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    +#+#
    -1.01
    ngdoc
    -0.88
    出版年
    -0.86
    ethene
    -0.86
    허
    -0.84
     Hobbs
    -0.82
    ">—
    -0.81
    expandindo
    -0.81
     McAllister
    -0.80
    thâu
    -0.79
    POSITIVE LOGITS
    Shade
    1.34
     Shade
    1.34
     Shades
    1.30
    shade
    1.30
    Shades
    1.26
     shade
    1.16
     shades
    1.15
    shades
    1.09
    Shady
    1.00
     shading
    0.96
    Activations Density 0.017%

    No Known Activations