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. 20-GEMMASCOPE-RES-131K
    6. 114641
    Prev
    Next
    INDEX
    Explanations

    references to economic exploitation and the dynamics of power struggles related to slavery and labor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     cured
    -0.32
     cuer
    -0.30
     kennen
    -0.30
     paired
    -0.30
     prior
    -0.30
    fiez
    -0.30
     dij
    -0.29
     sarili
    -0.28
     arac
    -0.28
     ся
    -0.28
    POSITIVE LOGITS
    stdc
    0.65
     Roskov
    0.64
    ViewFeatures
    0.63
     utafitiHapana
    0.62
    évaluateur
    0.60
     ब्रेकडाउन
    0.57
     kaarangay
    0.57
    AndroidJUnit
    0.56
    قایناقلار
    0.56
     autorytatywna
    0.54
    Activations Density 0.113%

    No Known Activations