© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11673
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to criminal convictions and sentencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Taking
    -0.44
     puissiez
    -0.42
    șe
    -0.42
     suceder
    -0.42
     adott
    -0.42
     HAPPENED
    -0.41
    ussch
    -0.41
    xmlns
    -0.41
    xyz
    -0.41
     ocurrir
    -0.40
    POSITIVE LOGITS
     sentencing
    1.28
     sentenced
    1.07
     convicted
    1.04
     convict
    1.03
     convicts
    1.00
     peniten
    0.95
     imprisonment
    0.93
     jail
    0.89
     prison
    0.88
     Parole
    0.88
    Activations Density 1.014%

    No Known Activations