© 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. 102522
    Prev
    Next
    INDEX
    Explanations

    terms related to geometric shapes and structures

    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
    AndEndTag
    -1.07
    expandindo
    -0.91
    RenderAtEndOf
    -0.83
     Italijanski
    -0.82
    DebuggerNonUser
    -0.80
     ब्रेकडाउन
    -0.79
    WriteTagHelper
    -0.76
     <<<<<<<<<<<<<<
    -0.76
    httphttps
    -0.74
    IsMutable
    -0.73
    POSITIVE LOGITS
     shape
    0.43
    Shape
    0.38
    shape
    0.37
     design
    0.36
     extré
    0.35
    shapes
    0.35
     ample
    0.34
     shapes
    0.33
     kształ
    0.33
    చు
    0.33
    Activations Density 0.013%

    No Known Activations