© 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. 39-GEMMASCOPE-RES-16K
    11. 5163
    Prev
    Next
    INDEX
    Explanations

    complex character emotions and societal expectations regarding individual identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ivelany
    -0.39
     skjø
    -0.38
    ýchod
    -0.37
     berangkat
    -0.35
    mäh
    -0.35
    ayuno
    -0.35
     przyzna
    -0.34
     dedica
    -0.33
     Stornier
    -0.32
    liptical
    -0.32
    POSITIVE LOGITS
     intrusion
    2.06
     intrusions
    1.87
     intrusive
    1.84
     intr
    1.79
     Intru
    1.74
     intru
    1.68
     invading
    1.67
     invade
    1.66
     invasion
    1.63
     interfering
    1.63
    Activations Density 0.818%

    No Known Activations