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. 80563
    Prev
    Next
    INDEX
    Explanations

    financial market terms and concepts related to stocks and investments

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

    stock market or financial news

    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
    معلومات
    -0.35
    rmtree
    -0.31
    èvent
    -0.31
     Creates
    -0.30
    *{-
    -0.30
    UrlEncoded
    -0.30
     Prä
    -0.30
     취
    -0.29
     Dör
    -0.28
    存在
    -0.28
    POSITIVE LOGITS
     Motley
    0.60
    afficheront
    0.59
    CppMethod
    0.55
    ScopeManager
    0.54
    featureID
    0.52
     ligiloj
    0.51
    postsleuth
    0.51
    BeginInit
    0.51
    ASX
    0.51
    IntoConstraints
    0.50
    Activations Density 0.002%

    No Known Activations