© 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. 15755
    Prev
    Next
    INDEX
    Explanations

    terms related to jail time and legal consequences

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

    phrases describing imprisonment, jail time, or prison sentences.

    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
    :✨
    -0.73
    Personendaten
    -0.69
    awakeFromNib
    -0.68
    出版年
    -0.67
     CreateTagHelper
    -0.66
    fjspx
    -0.63
    rungsseite
    -0.62
     autorytatywna
    -0.60
     CanadaChoose
    -0.59
    contentLoaded
    -0.58
    POSITIVE LOGITS
     jail
    1.30
     prison
    1.23
     Prison
    1.00
     imprisonment
    0.99
     imprisoned
    0.97
     jailed
    0.97
     Jail
    0.96
    jail
    0.95
     incarceration
    0.94
     incarcerated
    0.94
    Activations Density 0.392%

    No Known Activations