Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7536
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tree" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     Provisional
    -0.51
    ally
    -0.50
     QS
    -0.45
     Gina
    -0.44
     Thornton
    -0.43
     Anton
    -0.42
    Anton
    -0.41
    ardon
    -0.40
    lton
    -0.40
     Boon
    -0.40
    POSITIVE LOGITS
     Tree
    1.10
     Trees
    1.09
    Tree
    1.07
     TREE
    1.05
    Trees
    1.02
     tree
    1.02
     Bäume
    1.00
     trees
    0.98
     árvore
    0.95
    tree
    0.94
    Activations Density 0.116%

    No Known Activations