© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 101080
    Prev
    Next
    INDEX
    Explanations

    terms related to fiscal policies and their implications

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

    fiscal policy and economics

    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
    Name
    -0.54
    name
    -0.54
    TTT
    -0.54
    mother
    -0.53
    ADN
    -0.51
    WB
    -0.51
    People
    -0.50
     Bann
    -0.50
    ListNode
    -0.50
     newName
    -0.50
    POSITIVE LOGITS
     fiscal
    1.02
     Fiscal
    0.97
    Fiscal
    0.90
     FISCAL
    0.90
    fiscal
    0.88
     fiscale
    0.74
     fiscales
    0.73
     Fisk
    0.54
     fisk
    0.53
     budgetary
    0.52
    Activations Density 0.009%

    No Known Activations