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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6369
    Prev
    Next
    INDEX
    Explanations

    details related to tree species and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tabilité
    -0.44
     whey
    -0.44
     noodles
    -0.43
     tortilla
    -0.43
    şağı
    -0.43
     zebrafish
    -0.43
     quinoa
    -0.42
    Squid
    -0.41
    ukone
    -0.41
    siella
    -0.40
    POSITIVE LOGITS
     tree
    2.27
     trees
    2.22
     Trees
    2.01
     Tree
    2.01
     TREE
    1.94
    tree
    1.84
    Tree
    1.84
    Trees
    1.84
    trees
    1.79
     TREES
    1.77
    Activations Density 0.347%

    No Known Activations