© 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. 53633
    Prev
    Next
    INDEX
    Explanations

    references to strong or offensive language and profanity

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

    swearing and profanity

    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
    IsPostBack
    -0.52
    WithMany
    -0.46
    WithIOException
    -0.44
    HandlerContext
    -0.43
     Highlight
    -0.41
    
    -0.41
    ManagedBean
    -0.40
    DataAnnotations
    -0.40
     Leaves
    -0.40
    omitempty
    -0.39
    POSITIVE LOGITS
     swearing
    0.57
     profan
    0.50
     cursing
    0.46
     temper
    0.44
     swear
    0.43
     foul
    0.43
     profane
    0.42
    chließend
    0.41
     verbal
    0.40
     vocabulary
    0.40
    Activations Density 0.019%

    No Known Activations