Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 12392
    Prev
    Next
    INDEX
    Explanations

    terms related to folding or arrangements of objects or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MaterialApp
    -0.84
     resourceCulture
    -0.83
    +#+#
    -0.82
    aarrggbb
    -0.80
    BeginContext
    -0.78
    liesslich
    -0.77
    BeforeMethod
    -0.77
     Seeder
    -0.77
     actionPerformed
    -0.73
    /*
    -0.72
    POSITIVE LOGITS
     Fold
    1.03
     folded
    1.00
     folding
    0.97
     fold
    0.94
     folds
    0.92
    Fold
    0.91
     Folding
    0.88
    Folding
    0.88
    FOLD
    0.85
    Bent
    0.85
    Activations Density 0.374%

    No Known Activations