© 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. 16-GEMMASCOPE-RES-16K
    11. 5828
    Prev
    Next
    INDEX
    Explanations

    instances of coding structure, particularly involving the definition and manipulation of tree objects in programming

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

    Terms related to trees or tree structures

    np_acts-logits-general · gemini-2.0-flash

    tree structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bed
    -0.58
     Bed
    -0.53
     cama
    -0.50
    เก
    -0.50
    łos
    -0.48
     bedding
    -0.46
     track
    -0.46
     berp
    -0.46
     long
    -0.45
     behind
    -0.44
    POSITIVE LOGITS
     tree
    1.19
    Tree
    1.12
     Tree
    1.11
     TREE
    1.09
     subtree
    1.08
     trees
    1.08
     Trees
    1.05
    tree
    1.02
     TreeNode
    0.98
    trees
    0.98
    Activations Density 0.247%

    No Known Activations