© 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. 12-GEMMASCOPE-RES-16K
    11. 2604
    Prev
    Next
    INDEX
    Explanations

    instances of the word "determine" and its variations, indicating a focus on decision-making or establishing conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deleteAll
    -0.65
    Passenger
    -0.64
     sprays
    -0.63
    Gesellschaft
    -0.62
    Spaces
    -0.62
    Bakgrunnsstoff
    -0.61
     Passenger
    -0.59
    WhiteSpace
    -0.59
    Spacing
    -0.59
     pinulongan
    -0.59
    POSITIVE LOGITS
     determine
    1.25
    determine
    1.20
     determined
    1.18
     Determine
    1.17
    Determine
    1.13
     determination
    1.11
     determines
    1.07
     DETERMIN
    1.05
     determining
    1.04
    determined
    1.04
    Activations Density 0.189%

    No Known Activations