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. 7442
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to chemical synthesis processes and reactions

    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
     المعيارى
    -0.58
    medriver
    -0.58
    readystatechange
    -0.58
     estekak
    -0.56
     metav
    -0.56
    ChildScrollView
    -0.54
    Портал
    -0.53
    chloric
    -0.52
    Lymp
    -0.50
    crollView
    -0.48
    POSITIVE LOGITS
     compounds
    0.90
     compound
    0.86
     derivatives
    0.80
     synthesize
    0.74
     deriva
    0.74
     structurally
    0.74
     synthesized
    0.74
     Compounds
    0.74
     Compound
    0.73
     substituted
    0.72
    Activations Density 1.414%

    No Known Activations