© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 187
    Prev
    Next
    INDEX
    Explanations

    sentences discussing experiences and tips related to parenting and baby care

    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
    ผม
    -0.76
     אתה
    -0.71
     ผม
    -0.67
    俺は
    -0.66
    ครับ
    -0.66
    นะครับ
    -0.64
    אתה
    -0.63
    Obrigado
    -0.57
    僕は
    -0.57
    僕も
    -0.56
    POSITIVE LOGITS
     yummy
    0.84
     fabulous
    0.82
    ค่ะ
    0.81
    Obrigada
    0.78
     gorgeous
    0.78
     hubby
    0.75
     HUGE
    0.75
     loveliness
    0.73
     soooo
    0.72
     LOVED
    0.71
    Activations Density 2.168%

    No Known Activations