© 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 EvalsExportsAPI 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. 85256
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to legal sentencing and judicial processes

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

    legal sentencing outcomes

    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
     Kulit
    -0.30
     dinam
    -0.29
    oreille
    -0.29
    SLOW
    -0.29
    manera
    -0.29
     stá
    -0.28
     geist
    -0.28
     kulit
    -0.28
     redé
    -0.27
    étape
    -0.27
    POSITIVE LOGITS
     sentence
    1.37
     sentenced
    1.32
     sentences
    1.26
     sentencing
    1.13
     Sentences
    1.11
     Sentence
    1.10
     punishment
    1.08
    sentence
    1.03
    Sentence
    1.02
     jail
    0.98
    Activations Density 0.170%

    No Known Activations