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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15820
    Prev
    Next
    INDEX
    Explanations

    references to human trafficking and slavery

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

    "slavery" or "trafficking"

    np_acts-logits-general · gemini-2.0-flash

    trafficking and slavery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.58
    onViewCreated
    -0.56
    postsleuth
    -0.52
    
    -0.48
    -------
    -0.47
     mergeFrom
    -0.47
    MethodManager
    -0.46
     AssemblyCulture
    -0.46
    MLLoader
    -0.45
    AddTagHelper
    -0.45
    POSITIVE LOGITS
     trafficking
    1.25
     slavery
    1.16
     Trafficking
    1.09
     traff
    1.05
     slave
    1.02
     Slavery
    0.95
    slavery
    0.94
    slave
    0.90
     slaves
    0.88
    fficking
    0.88
    Activations Density 0.114%

    No Known Activations