© 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-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 11589
    Prev
    Next
    INDEX
    Explanations

    the concept of drawing or creating visual representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.46
    interopRequire
    -0.43
    endforeach
    -0.39
    |'\
    -0.38
    GetInstance
    -0.36
    tettu
    -0.36
    omitempty
    -0.36
    BeginContext
    -0.36
    zeb
    -0.35
    EndInit
    -0.35
    POSITIVE LOGITS
     Draw
    0.89
     draw
    0.83
     DRAW
    0.82
     drew
    0.81
     conclusions
    0.79
    Draw
    0.76
     Drawing
    0.75
     attention
    0.73
    draw
    0.72
     draws
    0.72
    Activations Density 0.102%

    No Known Activations