© 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. 18-GEMMASCOPE-RES-16K
    11. 1991
    Prev
    Next
    INDEX
    Explanations

    words reflecting social justice and racial inequality themes

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

    punishment and accountability

    np_acts-logits-general · gemini-2.0-flash

    legal consequences or recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.68
    TagMode
    -0.62
     linkovi
    -0.60
    Parcelize
    -0.58
    ViewImports
    -0.57
     beginnetje
    -0.54
    Gön
    -0.53
    ADATA
    -0.52
     invokingState
    -0.52
     gyhoeddwyd
    -0.52
    POSITIVE LOGITS
     punish
    1.12
     punishment
    1.09
     accountability
    1.04
     punished
    1.01
     prosecutions
    1.00
    pun
    0.96
     perpetrators
    0.95
     prosecute
    0.94
     retribution
    0.93
     Punishment
    0.92
    Activations Density 0.174%

    No Known Activations