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. 13484
    Prev
    Next
    INDEX
    Explanations

    specific Indian dishes or cuisine references

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

    Indian names, locations, and titles

    np_acts-logits-general · gemini-2.0-flash

    Indian minister positions

    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
    WebElementEntity
    -0.59
    styleable
    -0.54
     مشين
    -0.54
     chronique
    -0.53
     CHAPITRE
    -0.53
    งาม
    -0.53
    enumii
    -0.53
    ISLAM
    -0.51
    interopRequire
    -0.48
    autant
    -0.48
    POSITIVE LOGITS
     lorry
    0.67
     Coimbatore
    0.67
    batore
    0.64
    DockStyle
    0.64
    voor
    0.62
     Thiru
    0.61
    Tamil
    0.59
     Venkat
    0.59
     Tamil
    0.57
    icoot
    0.57
    Activations Density 0.173%

    No Known Activations