© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 705
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to the death penalty and its implementation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Sentences related to the death penalty

    np_acts-logits-general · gemini-2.0-flash

    death penalty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     للاسماء
    -0.49
    Quiénes
    -0.38
    RemoveField
    -0.36
    essoal
    -0.35
     culturelles
    -0.35
    ComponentScan
    -0.34
    CppMethod
    -0.33
     onOptions
    -0.33
     tất
    -0.33
     embreagem
    -0.33
    POSITIVE LOGITS
     myſelf
    0.59
     sentenced
    0.50
     convict
    0.49
     uſed
    0.48
     convicted
    0.47
    ADX
    0.47
     ſever
    0.47
     Sentence
    0.46
     raiſ
    0.46
     killers
    0.46
    Activations Density 0.932%

    No Known Activations