© 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. 4-GEMMASCOPE-RES-16K
    11. 9928
    Prev
    Next
    INDEX
    Explanations

    references to tree structures or trees in textual data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.21
     myſelf
    -1.16
     auffi
    -1.14
     ſeveral
    -1.13
     ―――――
    -1.13
     Jefus
    -1.11
     ſever
    -1.10
     pleaſure
    -1.10
     Majefty
    -1.09
     photolibrary
    -1.09
    POSITIVE LOGITS
     tree
    2.71
     Tree
    2.62
     TREE
    2.49
     trees
    2.41
    Tree
    2.36
    tree
    2.31
     Trees
    2.27
    TREE
    2.21
    Trees
    2.05
     TREES
    1.91
    Activations Density 0.028%

    No Known Activations