© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5041
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to financial or tax issues

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

    financial and monetary information, particularly amounts, transactions, and numerical values related to money and finances.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thus
    -0.56
     teils
    -0.54
     thus
    -0.53
     quizá
    -0.52
     asimismo
    -0.51
     dunque
    -0.51
    indeed
    -0.49
     således
    -0.48
     freilich
    -0.48
     zaś
    -0.48
    POSITIVE LOGITS
     Eſ
    0.72
     fashiola
    0.71
     Jefus
    0.71
     Inſ
    0.70
     Reſ
    0.70
    [@BOS@]
    0.68
     Diſ
    0.68
    <unused51>
    0.68
    <unused14>
    0.68
    <unused8>
    0.68
    Activations Density 1.103%

    No Known Activations