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. 10298
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and results related to particle physics

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

    Particle decay or decays

    np_acts-logits-general · gemini-2.0-flash

    hadronic W decays

    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
    WriteTagHelper
    -0.53
     calciatore
    -0.48
     AppCompatTheme
    -0.48
     pow
    -0.43
     Pow
    -0.42
    bitField
    -0.41
    uio
    -0.41
    HYDR
    -0.40
     προσ
    -0.39
     ujednoznacz
    -0.38
    POSITIVE LOGITS
     decay
    0.81
     decays
    0.80
     decaying
    0.73
     decayed
    0.69
    uxxxx
    0.68
     Decay
    0.68
     calendriers
    0.63
    orteur
    0.62
    decay
    0.60
     Antilles
    0.59
    Activations Density 0.313%

    No Known Activations