© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3057
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to child abuse offenses

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

    offence, guilty, or violation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    CodeAttribute
    -0.74
     AssemblyCulture
    -0.73
    complexContent
    -0.72
    发表于
    -0.67
    ंदीखरीदारी
    -0.62
     nahilalakip
    -0.62
    EndInit
    -0.62
    出版年
    -0.61
    Viitteet
    -0.60
    NOPQRST
    -0.60
    POSITIVE LOGITS
     knowingly
    0.87
     possession
    0.81
     anyone
    0.72
    Whoever
    0.71
     whoever
    0.67
     Whoever
    0.63
     person
    0.63
    Anyone
    0.60
    possession
    0.59
     Anyone
    0.59
    Activations Density 0.199%

    No Known Activations