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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6420
    Prev
    Next
    INDEX
    Explanations

    terms related to parent-child relationships in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
    ecap
    -0.51
     forma
    -0.48
    TagHelpers
    -0.47
    ServiceModel
    -0.46
     run
    -0.46
    PackageManager
    -0.46
    普
    -0.46
     running
    -0.45
    ressum
    -0.45
     Integrals
    -0.45
    POSITIVE LOGITS
     tree
    0.88
     TREE
    0.84
     hierarchy
    0.81
    Tree
    0.81
     hiér
    0.81
    tree
    0.81
    TREE
    0.80
     Tree
    0.78
     autorytatywna
    0.77
     trees
    0.75
    Activations Density 0.364%

    No Known Activations