© 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. 24-GEMMASCOPE-RES-16K
    11. 8404
    Prev
    Next
    INDEX
    Explanations

    details related to colors and their descriptions

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

    Colors, especially red, brown, and dark tones

    np_acts-logits-general · gemini-2.0-flash

    skin tone and shades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.58
    __":
    -0.52
    menistan
    -0.49
     crossorigin
    -0.48
     Kur
    -0.48
    IBOutlet
    -0.48
    clientHeight
    -0.47
    cipline
    -0.47
     مفص
    -0.46
    clientWidth
    -0.46
    POSITIVE LOGITS
     darker
    1.25
     darkening
    1.14
     darkest
    1.11
     darken
    1.06
     darkened
    1.03
     shade
    1.02
     shades
    1.01
     dark
    1.00
    dark
    0.95
     darkness
    0.89
    Activations Density 0.143%

    No Known Activations