Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12042
    Prev
    Next
    INDEX
    Explanations

    explicit descriptions of sexual interactions and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ]--;
    -0.67
    ")));
    
    -0.64
     onAnimation
    -0.60
     UIApplication
    -0.60
     aDecoder
    -0.58
    Abitanti
    -0.56
    ValueStyle
    -0.56
    acamata
    -0.55
     intptr
    -0.54
    umumkan
    -0.54
    POSITIVE LOGITS
     sexual
    1.98
     sex
    1.87
     sexually
    1.80
     Sexual
    1.73
     SEX
    1.62
     Sex
    1.62
    Sexual
    1.60
     erotic
    1.59
    Sex
    1.52
    sexual
    1.51
    Activations Density 0.590%

    No Known Activations