© 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. 11-GEMMASCOPE-RES-16K
    11. 9203
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "save" and related phrases about data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.60
     pageIndex
    -0.55
     userType
    -0.53
     eventId
    -0.51
    ruptedException
    -0.50
    RuleContext
    -0.50
     expressions
    -0.50
     columnIndex
    -0.49
     OCC
    -0.49
    FunctionType
    -0.49
    POSITIVE LOGITS
     save
    1.79
    save
    1.78
     Save
    1.70
    Save
    1.70
     saving
    1.66
     saves
    1.63
     saved
    1.62
    saving
    1.59
     SAVE
    1.58
    SAVE
    1.57
    Activations Density 0.110%

    No Known Activations