© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14655
    Prev
    Next
    INDEX
    Explanations

    structured data representations, particularly trees and their nodes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoField
    -0.53
    ecap
    -0.49
    awtextra
    -0.48
    Revenir
    -0.44
     tấm
    -0.43
     @"/
    -0.43
    Portail
    -0.42
    messageInfo
    -0.41
     AssemblyCompany
    -0.40
     cape
    -0.39
    POSITIVE LOGITS
     tree
    1.60
     subtree
    1.51
     Tree
    1.47
    Tree
    1.40
     TREE
    1.35
    tree
    1.34
     trees
    1.28
    TREE
    1.27
     root
    1.25
     TreeNode
    1.24
    Activations Density 0.641%

    No Known Activations