© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 11639
    Prev
    Next
    INDEX
    Explanations

    phrases related to reassurance and alleviating concerns

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    AndEndTag
    -0.82
    ſelf
    -0.60
    parsedMessage
    -0.55
     Cæsar
    -0.54
    addCriterion
    -0.53
    expandindo
    -0.51
     Modif
    -0.51
     intoler
    -0.51
     onStop
    -0.51
    tagonal
    -0.49
    POSITIVE LOGITS
     reassured
    1.01
     reassurance
    0.99
     reassure
    0.94
     reassuring
    0.94
     assurance
    0.75
     assured
    0.73
     assuring
    0.71
     assurances
    0.67
     assure
    0.65
    安心
    0.64
    Activations Density 0.349%

    No Known Activations