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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6213
    Prev
    Next
    INDEX
    Explanations

    elements of programming code related to graphical operations and path manipulation

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

    Drawing and path-related code

    np_acts-logits-general · gemini-2.0-flash

    draw graphics and paths

    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
     Waray
    -0.67
    LoadScene
    -0.56
    shtml
    -0.53
    chium
    -0.52
     rosto
    -0.51
    athus
    -0.51
     contended
    -0.50
    lampen
    -0.50
    deniz
    -0.49
     Rear
    -0.49
    POSITIVE LOGITS
     draw
    0.69
     brush
    0.68
     DRAW
    0.66
     strokes
    0.66
     drawing
    0.65
     Draw
    0.60
     drew
    0.59
     draws
    0.59
     stroke
    0.58
     Drawn
    0.58
    Activations Density 0.393%

    No Known Activations