© 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. 4584
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and law enforcement processes, particularly arrest warrants and related actions

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

    legal terms and phrases related to criminal proceedings, particularly words indicating arrest, warrants, and prosecution.

    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
    __*/
    -0.43
     Umständen
    -0.38
    出版年
    -0.36
     pérdidas
    -0.36
    Források
    -0.36
     fallecido
    -0.35
    Losing
    -0.34
    setLabel
    -0.34
     vertrou
    -0.34
     pérdida
    -0.34
    POSITIVE LOGITS
     arrest
    2.31
     arrested
    2.13
     arrests
    2.02
     Arrest
    1.99
    Arrest
    1.87
    arrest
    1.84
     Arrested
    1.68
     arresting
    1.55
    逮捕
    1.53
     ditangkap
    1.30
    Activations Density 0.589%

    No Known Activations