© 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. 22-GEMMASCOPE-RES-16K
    11. 6274
    Prev
    Next
    INDEX
    Explanations

    actions and processes, particularly those involving interaction or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     häl
    -0.54
     quæ
    -0.54
    schrank
    -0.52
     dieux
    -0.52
    ))^
    -0.50
     perfección
    -0.49
     houſe
    -0.49
    område
    -0.49
    )))))
    -0.48
     gæ
    -0.47
    POSITIVE LOGITS
    ing
    1.09
    ING
    1.05
    ting
    0.95
    ating
    0.91
    ging
    0.91
    ering
    0.88
    ding
    0.87
    ning
    0.86
    ening
    0.86
    aming
    0.85
    Activations Density 1.639%

    No Known Activations