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. 2490
    Prev
    Next
    INDEX
    Explanations

    terms related to diet, energy expenditure, and metabolic measurements

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

    Metabolism or time-related words

    np_acts-logits-general · gemini-2.0-flash

    metabolic processes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     estoppel
    -0.55
     malpractice
    -0.55
     encephalitis
    -0.54
    abestanden
    -0.53
    同士
    -0.51
     agrav
    -0.51
     Malware
    -0.50
    ision
    -0.50
     virulence
    -0.49
     AIDS
    -0.48
    POSITIVE LOGITS
     metabolic
    0.76
    OGND
    0.74
     Penh
    0.71
    olisme
    0.67
    Metabolic
    0.66
     tiss
    0.66
    TagMode
    0.65
     metabolism
    0.64
     Metabolic
    0.63
     الحره
    0.62
    Activations Density 2.212%

    No Known Activations