© 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. 7-GEMMASCOPE-RES-16K
    11. 12282
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their actions or experiences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     held
    -0.37
     &
    -0.35
    ˌ
    -0.35
    -
    -0.35
     (
    -0.34
    dic
    -0.34
    ti
    -0.34
     whose
    -0.34
     seeks
    -0.33
     seated
    -0.33
    POSITIVE LOGITS
     him
    0.87
     autorytatywna
    0.84
    AddTagHelper
    0.80
    AndEndTag
    0.79
    featureID
    0.75
    MLLoader
    0.74
    Him
    0.73
    herself
    0.71
    webElementGuid
    0.71
     honom
    0.70
    Activations Density 0.220%

    No Known Activations