© 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. 8112
    Prev
    Next
    INDEX
    Explanations

    categories and classification labels

    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
     pleaſure
    -0.81
     leaſt
    -0.79
     itſelf
    -0.73
     queſta
    -0.71
    ArrowToggle
    -0.71
     myſelf
    -0.68
     ſta
    -0.68
     ſte
    -0.67
     betweenstory
    -0.67
     fubject
    -0.67
    POSITIVE LOGITS
     יוד
    0.39
     ciência
    0.38
     estampa
    0.38
     supérieures
    0.37
     referência
    0.36
     banderas
    0.35
    zelfde
    0.35
     asiático
    0.35
     Sprach
    0.35
     références
    0.34
    Activations Density 0.465%

    No Known Activations