Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 73707
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to rights, governmental actions, and courtroom procedures

    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
    JpaRepository
    -0.38
    sk
    -0.38
    BeNil
    -0.37
    CppMethod
    -0.35
    ViewFeatures
    -0.35
     pageContext
    -0.35
    InjectMocks
    -0.35
    StartCoroutine
    -0.33
     Ever
    -0.32
     neust
    -0.32
    POSITIVE LOGITS
     '\\;'
    0.71
    parsedMessage
    0.55
    numerusform
    0.54
     richtet
    0.52
     thereunder
    0.50
    QMetaType
    0.49
    Хьажоргаш
    0.48
    
    0.48
    DrawerToggle
    0.47
     ब्रेकडाउन
    0.47
    Activations Density 0.206%

    No Known Activations