© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 14832
    Prev
    Next
    INDEX
    Explanations

    phrases related to folding and handling materials, particularly in a crafting or textile context

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

    folding and wrapping materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     regalías
    -0.47
    principalColumn
    -0.47
     iprot
    -0.44
    وردار
    -0.43
     fédé
    -0.43
    AutoField
    -0.42
     InputDecoration
    -0.42
     nonatomic
    -0.40
     sogget
    -0.39
    änä
    -0.39
    POSITIVE LOGITS
     origami
    0.68
     twist
    0.58
     wrapping
    0.57
     folded
    0.56
     twisting
    0.55
    origami
    0.54
     wrap
    0.52
     fold
    0.52
     Twist
    0.52
     twists
    0.52
    Activations Density 0.021%

    No Known Activations