© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10760
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical structures related to trees

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

    the word "tree" in various contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.38
     zw
    -0.36
    PLICIT
    -0.35
     Anton
    -0.34
     Explicit
    -0.33
    ➩
    -0.33
    })+
    -0.33
    شون
    -0.32
    derung
    -0.32
    lishes
    -0.32
    POSITIVE LOGITS
     Tree
    0.87
     TREE
    0.82
     tree
    0.79
    Tree
    0.77
    TREE
    0.76
     Trees
    0.74
    árbol
    0.72
     树
    0.71
     Bäume
    0.71
     trees
    0.69
    Activations Density 0.074%

    No Known Activations