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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 5939
    Prev
    Next
    INDEX
    Explanations

    technical jargon and terminology related to chemistry and biochemistry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Abbreviations/acronyms in parentheses

    np_acts-logits-general · gemini-2.0-flash

    abbreviations for biological molecules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     com
    -0.75
     er
    -0.73
     
    -0.73
     T
    -0.72
     int
    -0.72
     re
    -0.71
     o
    -0.71
     de
    -0.71
     an
    -0.70
     ar
    -0.70
    POSITIVE LOGITS
     avoient
    1.48
     étoient
    1.44
     feroit
    1.43
     auroit
    1.40
     enfans
    1.38
     AssemblyCulture
    1.37
     varandra
    1.34
     femininas
    1.32
     démocr
    1.29
     étoit
    1.27
    Activations Density 0.868%

    No Known Activations