Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16-GEMMASCOPE-RES-16K
    6. 42
    Prev
    Next
    INDEX
    Explanations

    concepts related to phonons and their interactions in materials, particularly in the context of optical properties and scattering phenomena

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

    Spin-phonon interactions or phonon decay

    np_acts-logits-general · gemini-2.0-flash

    magnetic, phonon, and scattering processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Conne
    -0.52
     
    -0.45
     päiv
    -0.45
     Conne
    -0.45
    Comparative
    -0.44
     Shi
    -0.44
     paja
    -0.44
     national
    -0.43
    łącz
    -0.43
     #
    -0.43
    POSITIVE LOGITS
    ftagPool
    0.91
     GenerationType
    0.88
    MLLoader
    0.86
     يتيمه
    0.86
    MENAFN
    0.85
     оригіналу
    0.84
     فريبيس
    0.83
    脚注の使い方
    0.82
     سكانية
    0.82
    CppCodeGen
    0.82
    Activations Density 2.608%

    No Known Activations