© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14855
    Prev
    Next
    INDEX
    Explanations

    terms related to connections or ties between objects or concepts

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

    knots and tying

    np_acts-logits-general · gemini-2.0-flash

    tie to or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     betweenstory
    -0.86
    ✨:
    -0.83
    +#+
    -0.83
     تضيفلها
    -0.82
     utafitiHapana
    -0.79
    Бахар
    -0.76
    ChildScrollView
    -0.76
    Vidite
    -0.75
    mybatisplus
    -0.74
    reportWebVitals
    -0.73
    POSITIVE LOGITS
     knots
    0.91
     ties
    0.84
     knot
    0.82
     Ties
    0.73
     tied
    0.72
     tie
    0.65
     Knot
    0.64
    knot
    0.63
    tie
    0.60
     tying
    0.59
    Activations Density 0.114%

    No Known Activations