© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 12319
    Prev
    Next
    INDEX
    Explanations

    conversations about unity and shared experiences among people

    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
     твое
    -0.61
     אתה
    -0.61
     твои
    -0.59
     לך
    -0.56
     твой
    -0.55
     хочешь
    -0.54
     твоя
    -0.53
     будешь
    -0.52
     senin
    -0.52
     deines
    -0.52
    POSITIVE LOGITS
     yourselves
    1.85
     jullie
    1.53
     yall
    1.48
    你们
    1.41
    你們
    1.38
     vocês
    1.38
     kalian
    1.13
    你们的
    1.07
     ustedes
    1.00
     guys
    0.91
    Activations Density 0.182%

    No Known Activations