© 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. 16-GEMMASCOPE-RES-16K
    11. 12760
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or comparisons, particularly focusing on the concept of "between."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.68
     auroit
    -0.60
    mstyle
    -0.56
     avoient
    -0.53
     pleaſure
    -0.53
     feroit
    -0.50
     pouvoit
    -0.50
     âmes
    -0.49
    ſelf
    -0.48
     épaules
    -0.48
    POSITIVE LOGITS
     between
    1.71
    Between
    1.56
    between
    1.55
     Between
    1.55
    BETWEEN
    1.38
     BETWEEN
    1.35
     между
    1.34
     zwischen
    1.33
     між
    1.24
     tussen
    1.20
    Activations Density 0.101%

    No Known Activations