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. 2587
    Prev
    Next
    INDEX
    Explanations

    elements of recognition and award ceremonies

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

    Ceremonies, awards, announcements

    np_acts-logits-general · gemini-2.0-flash

    award ceremony

    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
    GraphicsUnit
    -0.65
     FetchType
    -0.63
     consultato
    -0.55
     فريبيس
    -0.55
     pinulongan
    -0.54
     تانيه
    -0.53
    lexikon
    -0.49
    rafts
    -0.49
    ilarang
    -0.49
    vanna
    -0.49
    POSITIVE LOGITS
     ceremony
    1.57
     ceremonies
    1.37
     Ceremony
    1.32
     ceremon
    1.22
     ceremonial
    1.20
     Ceremonies
    1.16
     ceremonia
    1.16
     Ceremon
    1.10
     cerim
    1.08
     cerimonia
    1.04
    Activations Density 0.144%

    No Known Activations