© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11296
    Prev
    Next
    INDEX
    Explanations

    terms related to folding or folded structures

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

    Refers to the action of folding

    np_acts-logits-general · gemini-2.0-flash

    fold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andExpect
    -0.77
    WebVitals
    -0.68
     doInBackground
    -0.64
    imageshack
    -0.62
     ExecuteAsync
    -0.61
    yntaxException
    -0.60
    ituary
    -0.59
    γραφή
    -0.57
    WithFormat
    -0.56
     sessionFactory
    -0.56
    POSITIVE LOGITS
     Fold
    0.92
     fold
    0.89
     folds
    0.89
     folding
    0.89
     Folding
    0.88
    Folding
    0.86
     origami
    0.83
    folding
    0.81
     Fol
    0.79
     folded
    0.78
    Activations Density 0.145%

    No Known Activations