© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6583
    Prev
    Next
    INDEX
    Explanations

    references to leaves and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndProject
    -1.18
     XCTest
    -0.91
    TargetException
    -0.90
     ControllerBase
    -0.79
     متعلقه
    -0.77
    MemoryWarning
    -0.76
    Demografie
    -0.75
    makeConstraints
    -0.75
    Хьажоргаш
    -0.74
    Życiorys
    -0.74
    POSITIVE LOGITS
     leaf
    2.88
     Leaf
    2.71
    leaf
    2.60
    Leaf
    2.52
     LEAF
    2.37
     leaves
    2.21
    LEAF
    2.16
     Leaves
    2.11
    Leaves
    2.10
    leaves
    2.09
    Activations Density 0.096%

    No Known Activations