© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3121
    Prev
    Next
    INDEX
    Explanations

    references to operations and processes in a technical or computational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "operation" or "operations"

    np_acts-logits-general · gemini-2.0-flash

    operation(s)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageState
    -0.44
     StatelessWidget
    -0.43
     trưng
    -0.40
    HeaderText
    -0.40
    kend
    -0.39
     Lithuanian
    -0.38
     createState
    -0.38
    calipsis
    -0.37
     alcanzado
    -0.37
    BaseAdapter
    -0.36
    POSITIVE LOGITS
     operation
    2.06
     operations
    2.05
     Operation
    2.00
     Operations
    1.95
    operations
    1.93
    Operation
    1.89
    Operations
    1.85
    operation
    1.80
     OPERATION
    1.77
     OPERATIONS
    1.77
    Activations Density 0.141%

    No Known Activations