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. 2581
    Prev
    Next
    INDEX
    Explanations

    references to military forces and their historical context

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

    Vietnamese locations or contexts

    np_acts-logits-general · gemini-2.0-flash

    Vietnamese names and places

    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
    TagMode
    -0.55
     >=",
    -0.55
    횟
    -0.45
    bukkit
    -0.44
    ţ
    -0.43
    ٱ
    -0.43
    ț
    -0.43
     bpy
    -0.43
     Cec
    -0.42
    ValueGenerated
    -0.41
    POSITIVE LOGITS
     Vietnam
    1.28
     Vietnamese
    1.22
    Vietnam
    1.18
     vietnam
    1.07
     Hanoi
    1.06
     Viet
    1.02
     VIET
    1.00
     Saigon
    0.99
    Viet
    0.97
    Vietnamese
    0.95
    Activations Density 0.141%

    No Known Activations