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 - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 813
    Prev
    Next
    INDEX
    Explanations

    numerical values and rates related to stock dividends and financial metrics

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

    financial calculations and rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     almost
    -0.39
    ContentAsync
    -0.37
    mayın
    -0.37
    audiovisuel
    -0.36
     Приступљено
    -0.36
    Almost
    -0.36
    ].(
    -0.36
     nearly
    -0.35
     הנו
    -0.35
     prácticamente
    -0.35
    POSITIVE LOGITS
    RegressionTest
    0.63
     utafitiHapana
    0.60
     propOrder
    0.59
    
    0.57
     JpaRepository
    0.57
    UnusedPrivate
    0.56
    ViewImports
    0.56
    LabelTagHelper
    0.55
    хьтан
    0.55
    UserScript
    0.54
    Activations Density 0.110%

    No Known Activations