© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5093
    Prev
    Next
    INDEX
    Explanations

    terms related to pedophilia

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

    starting with "ped" or "Cab"

    np_acts-logits-general · gemini-2.0-flash

    ped and Cab variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loma
    -0.51
    ynb
    -0.51
    Reporting
    -0.48
    #+#
    -0.47
     comp
    -0.47
    GAL
    -0.46
     margin
    -0.46
     ObjectParameter
    -0.45
    ímite
    -0.44
    例句
    -0.44
    POSITIVE LOGITS
     Administrativna
    0.70
     EconPapers
    0.62
     wireType
    0.57
     schaff
    0.57
     Мексичка
    0.56
     HasFactory
    0.54
    تقاوى
    0.53
    ншни
    0.53
    agree
    0.53
     Meilleures
    0.53
    Activations Density 0.245%

    No Known Activations