© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 6213
    Prev
    Next
    INDEX
    Explanations

    elements related to moral or social concerns, particularly in reference to potential negative influences or vices

    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
    PropertyChanging
    -0.51
     تكبرها
    -0.50
    httphttps
    -0.48
    PMailer
    -0.48
     Италијани
    -0.47
    OrWhiteSpace
    -0.46
    ferrer
    -0.46
    المكان
    -0.45
    hamilan
    -0.45
    ьажоргаш
    -0.44
    POSITIVE LOGITS
     D
    1.00
     d
    0.87
    D
    0.69
     DR
    0.68
     Д
    0.68
     DT
    0.64
     الد
    0.63
    getD
    0.61
     ד
    0.61
     드
    0.61
    Activations Density 2.494%

    No Known Activations