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. 3-GEMMASCOPE-RES-16K
    6. 10999
    Prev
    Next
    INDEX
    Explanations

    terminology related to drug and metabolic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eup
    -0.54
     Calais
    -0.52
     Vele
    -0.52
    randomUUID
    -0.51
     SAMSUNG
    -0.51
     Sare
    -0.51
     phil
    -0.51
    객
    -0.50
    ATAR
    -0.50
    fflush
    -0.49
    POSITIVE LOGITS
     enzyme
    1.41
     Enzymes
    1.31
     enzymatic
    1.29
     Enzyme
    1.27
     enzymes
    1.27
    Enzyme
    1.15
    酶
    1.09
    enzyme
    1.07
     enz
    1.03
     Enzy
    1.02
    Activations Density 1.135%

    No Known Activations