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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8800
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to mechanical stresses and material durability

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

    temperature, radiation, flow, energy, movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     autorytatywna
    -0.77
    jsxFileName
    -0.72
    addContainerGap
    -0.71
    CppMethod
    -0.69
    InsertCommand
    -0.69
    存于互联网档案馆
    -0.68
    GEBURTS
    -0.66
     IBOutlet
    -0.64
    RegressionTest
    -0.63
    ReusableCell
    -0.63
    POSITIVE LOGITS
     during
    0.27
    出版年
    0.26
     sub
    0.25
     aceptas
    0.24
     grade
    0.22
     raggi
    0.22
     degrees
    0.22
     liquor
    0.22
     pressure
    0.22
     læng
    0.22
    Activations Density 0.056%

    No Known Activations