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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 244
    Prev
    Next
    INDEX
    Explanations

    terms related to physical models and mathematical expressions in theoretical physics

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

    complex mathematical notation and symbols, particularly related to physics and quantum mechanics equations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Administrativna
    -0.46
     Мексичка
    -0.43
     Савезне
    -0.40
    exitRule
    -0.39
    FindBy
    -0.36
    錐
    -0.36
     Kali
    -0.35
    #
    -0.34
     núm
    -0.34
     endblock
    -0.33
    POSITIVE LOGITS
     contribution
    0.74
     contributions
    0.73
     contributo
    0.66
     contribución
    0.65
     Contribution
    0.62
    contributions
    0.61
     Contributions
    0.59
     CONTRIBUTION
    0.58
    contribution
    0.57
     CONTRIBUTIONS
    0.56
    Activations Density 1.006%

    No Known Activations