© 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. 9-GEMMASCOPE-RES-16K
    11. 14539
    Prev
    Next
    INDEX
    Explanations

    references to mothers and maternal relationships

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
    Negative Logits
     насељу
    -0.67
     snippetHide
    -0.66
    featureID
    -0.64
    RenderAtEndOf
    -0.61
     Paglinawan
    -0.58
    AndEndTag
    -0.57
    UnusedPrivate
    -0.57
     Pegasus
    -0.57
     CreateTagHelper
    -0.57
     transfieras
    -0.56
    POSITIVE LOGITS
     mother
    1.84
     Mother
    1.81
    Mother
    1.75
     MOTHER
    1.63
    mother
    1.57
    MOTHER
    1.48
     mothers
    1.42
     Mothers
    1.41
    Mothers
    1.34
     moeder
    1.33
    Activations Density 0.149%

    No Known Activations