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. 13996
    Prev
    Next
    INDEX
    Explanations

    species-related terminology in biological contexts

    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
    PHeader
    -0.60
    ttino
    -0.58
     ducks
    -0.57
     radeon
    -0.57
     swans
    -0.56
     Galo
    -0.55
     Nieren
    -0.53
     forState
    -0.53
     catar
    -0.52
     dolphin
    -0.52
    POSITIVE LOGITS
     insect
    1.08
     bugs
    1.05
     spiders
    1.02
     spider
    1.02
     Insect
    0.99
     bug
    0.99
     insects
    0.98
     Spider
    0.92
     Bugs
    0.91
     Bug
    0.90
    Activations Density 0.338%

    No Known Activations