© 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. 27-GEMMASCOPE-RES-16K
    11. 12646
    Prev
    Next
    INDEX
    Explanations

    expressions related to the diversity and comprehensiveness of a media collection

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     inspiração
    -0.45
     inspiración
    -0.36
     tents
    -0.35
     drafts
    -0.34
    Clo
    -0.33
     poh
    -0.33
     계
    -0.33
    draft
    -0.33
     inspiration
    -0.33
     Cher
    -0.33
    POSITIVE LOGITS
     remastered
    0.75
     remaster
    0.74
     reissue
    0.73
     DVD
    0.72
     discs
    0.62
    DVD
    0.62
     archival
    0.59
     DVDs
    0.59
     digitally
    0.59
     dvd
    0.59
    Activations Density 0.268%

    No Known Activations