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. 12-GEMMASCOPE-RES-16K
    6. 12515
    Prev
    Next
    INDEX
    Explanations

    references to biological studies and experimental methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.62
     ویکی‌پدیا
    -0.61
    standen
    -0.57
    banken
    -0.53
    <eos>
    -0.51
    ppure
    -0.49
     rembour
    -0.49
     đẳng
    -0.48
    CppMethod
    -0.48
    jukan
    -0.48
    POSITIVE LOGITS
     utafitiHapana
    0.92
    WebVitals
    0.88
    oredCriteria
    0.74
     autorytatywna
    0.67
     MenuView
    0.62
    rungsseite
    0.62
     ddelweddau
    0.61
     الدولى
    0.60
    soort
    0.59
    はじめに
    0.59
    Activations Density 1.317%

    No Known Activations