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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 62508
    Prev
    Next
    INDEX
    Explanations

    phrases related to tax-related issues and financial obligations

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

    money paid in taxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    appliquent
    -0.29
    PreferredItem
    -0.23
     vlastní
    -0.22
     propias
    -0.22
     propia
    -0.20
    AutoScaleMode
    -0.20
     mesmas
    -0.20
     usein
    -0.19
     mismas
    -0.19
     ruptura
    -0.19
    POSITIVE LOGITS
     billions
    1.77
     $\$
    1.67
     £
    1.60
     millions
    1.54
     \$
    1.52
     ~$
    1.51
     €
    1.50
    millions
    1.48
     Millions
    1.40
     $
    1.38
    Activations Density 0.235%

    No Known Activations