© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105635
    Prev
    Next
    INDEX
    Explanations

    concepts related to ethical or moral dilemmas involving exploitation and sacrifice

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

    still frequency racist exploitation own

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.45
     nonatomic
    -0.35
    帖最后由
    -0.34
     препратки
    -0.33
     Operating
    -0.33
     ModelExpression
    -0.33
     تضيفلها
    -0.32
    Operating
    -0.32
     operating
    -0.32
     Tema
    -0.32
    POSITIVE LOGITS
     still
    0.54
    still
    0.48
     disambiguazione
    0.47
     defaultstate
    0.47
     STILL
    0.47
     Still
    0.46
    Still
    0.46
    kloped
    0.45
    WireFormat
    0.43
     ainda
    0.43
    Activations Density 0.151%

    No Known Activations