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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1835
    Prev
    Next
    INDEX
    Explanations

    financial and economic terminology, particularly related to income, budgets, and financial support structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.72
    yntaxException
    -0.67
     Италијани
    -0.60
     increí
    -0.59
     AssemblyTitle
    -0.59
    tagHelperRunner
    -0.58
     estadounid
    -0.56
    
    -0.56
    AccessorTable
    -0.56
    setContentView
    -0.55
    POSITIVE LOGITS
    -/
    0.44
    -
    0.35
     parliamentary
    0.34
     civilian
    0.32
     oral
    0.32
     horizontal
    0.32
    nesses
    0.32
    "/"
    0.31
     democratic
    0.31
    ressional
    0.31
    Activations Density 1.865%

    No Known Activations