© 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. 12-GEMMASCOPE-RES-16K
    11. 7934
    Prev
    Next
    INDEX
    Explanations

    phrases centered around the concept of standing or positioning

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    الحياه
    -0.48
     muualla
    -0.47
    wege
    -0.45
     autorytatywna
    -0.44
     deluge
    -0.43
     CID
    -0.42
    reif
    -0.42
     AppCompatTheme
    -0.42
     McCoy
    -0.41
     routes
    -0.40
    POSITIVE LOGITS
     Stand
    1.47
     STAND
    1.45
     stand
    1.44
    Stand
    1.41
     standing
    1.33
     stands
    1.27
     Stands
    1.23
     stood
    1.23
    Standing
    1.21
     Standing
    1.20
    Activations Density 0.097%

    No Known Activations