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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2795
    Prev
    Next
    INDEX
    Explanations

    legislative language related to laws and their enforcement

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

    words and phrases related to statutes, legislation, and legal enactments.

    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
    SequentialGroup
    -0.63
    이션
    -0.39
    RTEX
    -0.37
    utación
    -0.37
     рассказ
    -0.36
    UrlResolution
    -0.36
     spirituelle
    -0.36
     πραγ
    -0.35
    ✭✭
    -0.34
     Organizador
    -0.33
    POSITIVE LOGITS
     legislation
    1.26
     legisl
    1.15
     legislative
    1.14
     legis
    1.06
     laws
    1.00
     legal
    1.00
    legislation
    0.95
     Legislation
    0.94
     codif
    0.92
     repeal
    0.91
    Activations Density 0.764%

    No Known Activations