© 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. 11073
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to court judgments

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

    legal and formal document language, particularly words and punctuation associated with court decisions and legal proceedings.

    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
    olism
    -0.32
     esquecer
    -0.32
    くれました
    -0.31
     Vikipedi
    -0.30
     étudier
    -0.30
     exprimer
    -0.30
     yeterli
    -0.30
     prévoir
    -0.30
     vez
    -0.29
     współpra
    -0.29
    POSITIVE LOGITS
     defendant
    1.72
     defendants
    1.61
     plaintiff
    1.59
    defendant
    1.43
     plaintiffs
    1.43
    Defendant
    1.43
     Defendant
    1.38
     Plaintiff
    1.27
     Defendants
    1.27
     respondent
    1.26
    Activations Density 2.975%

    No Known Activations