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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101586
    Prev
    Next
    INDEX
    Explanations

    geometric shapes, particularly cubes and squares

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    setopt
    -0.42
     Zust
    -0.38
    IGraphics
    -0.37
     diharapkan
    -0.37
    ResponseWriter
    -0.36
     mencegah
    -0.35
     eenige
    -0.35
     befind
    -0.35
     temprana
    -0.35
     liggen
    -0.35
    POSITIVE LOGITS
     cube
    1.22
     cubes
    0.97
     Cube
    0.96
     rectangle
    0.91
    Cube
    0.90
    cube
    0.87
     Cubes
    0.83
     box
    0.82
     cubo
    0.82
     square
    0.81
    Activations Density 0.032%

    No Known Activations