© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 122953
    Prev
    Next
    INDEX
    Explanations

    mentions of people, specifically emphasizing gendered references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     the
    -0.37
    raise
    -0.36
     definition
    -0.36
    PET
    -0.35
    Definition
    -0.35
     بای
    -0.34
    roll
    -0.34
     الص
    -0.34
    down
    -0.34
     lauf
    -0.34
    POSITIVE LOGITS
     Monfieur
    0.83
     ſta
    0.82
     whoſe
    0.81
     perſon
    0.81
     pleaſure
    0.80
     houſe
    0.80
     ſch
    0.77
     Majefty
    0.77
    tanleria
    0.76
     chofe
    0.76
    Activations Density 0.022%

    No Known Activations