© 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. 87065
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal status and criminal background

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

    past events or lack thereof

    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
     <<<<<<<<<<<<<<
    -0.54
     épar
    -0.42
     pain
    -0.36
    φέρ
    -0.34
    Rè
    -0.34
     agon
    -0.34
    hoek
    -0.34
    毋
    -0.33
     douleur
    -0.33
    Размеры
    -0.33
    POSITIVE LOGITS
     pernah
    0.79
    曾
    0.67
     disqual
    0.66
     felony
    0.65
     convicted
    0.64
    เคย
    0.63
     Italijanski
    0.61
     bankrupt
    0.61
     criminal
    0.61
     disqualified
    0.58
    Activations Density 0.096%

    No Known Activations