© 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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10962
    Prev
    Next
    INDEX
    Explanations

    descriptions and characteristics of new plant varieties, specifically fruit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.90
    IntoConstraints
    -0.79
     MenuView
    -0.74
    TintMode
    -0.72
     GenerationType
    -0.71
     насељу
    -0.69
     BorderSide
    -0.69
    setVerticalGroup
    -0.68
    :✨
    -0.66
    featureID
    -0.65
    POSITIVE LOGITS
    enterOuterAlt
    0.36
    ↵↵
    0.28
     pears
    0.28
     melons
    0.28
    "
    0.27
     apples
    0.27
     delin
    0.26
     علا
    0.25
    Peak
    0.25
    <bos>
    0.25
    Activations Density 0.395%

    No Known Activations