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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1639
    Prev
    Next
    INDEX
    Explanations

    references to economic or financial topics related to taxes and energy companies

    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
     surla
    -0.82
     &___
    -0.75
    MigrationBuilder
    -0.64
     capitalization
    -0.63
    extAlignment
    -0.62
    AccessorTable
    -0.62
     optimizations
    -0.61
     AMERICAN
    -0.61
     legalization
    -0.61
    ThemeOverlay
    -0.60
    POSITIVE LOGITS
     brilliant
    0.49
     fantastic
    0.45
    brilliant
    0.42
     communities
    0.42
     brilliantly
    0.40
     Britain
    0.39
    Britain
    0.39
     Brilliant
    0.38
    Brilliant
    0.38
     brilhante
    0.36
    Activations Density 0.215%

    No Known Activations