© 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. 20-GEMMASCOPE-RES-16K
    11. 339
    Prev
    Next
    INDEX
    Explanations

    terms related to spatial regions and areas in data analysis

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

    "Area" followed by measurements or spatial contexts

    np_acts-logits-general · gemini-2.0-flash

    area under curve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.81
    🏻
    -0.70
     HasFactory
    -0.69
    ftagPool
    -0.69
    --}}
    -0.66
    MessageTagHelper
    -0.65
    🏼
    -0.60
    AndEndTag
    -0.59
    ybė
    -0.59
    writeHead
    -0.58
    POSITIVE LOGITS
     areas
    0.87
     AREA
    0.86
     area
    0.86
     rug
    0.86
     rugs
    0.84
     Areas
    0.80
    Areas
    0.77
    areas
    0.77
     Area
    0.76
    area
    0.76
    Activations Density 0.126%

    No Known Activations