© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 451
    Prev
    Next
    INDEX
    Explanations

    references to sexual activity and explicit content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppCodeGen
    -0.56
     newBuilder
    -0.46
    InputBorder
    -0.44
     intStringLen
    -0.44
     للمعارف
    -0.44
     surla
    -0.44
    MessageOf
    -0.43
    ThroughAttribute
    -0.43
     defaultstate
    -0.43
     pouvoit
    -0.43
    POSITIVE LOGITS
     sexual
    2.16
     sex
    2.02
     sexually
    1.85
     Sexual
    1.84
    Sexual
    1.78
    sexual
    1.77
     SEX
    1.71
     Sex
    1.67
     sexu
    1.63
    sex
    1.59
    Activations Density 0.915%

    No Known Activations