© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105302
    Prev
    Next
    INDEX
    Explanations

    specific entities or categories relevant to systems, health, and organizational structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ########.
    -0.85
     betweenstory
    -0.84
    TagMode
    -0.84
    IUrlHelper
    -0.82
    tvguidetime
    -0.80
    MessageOf
    -0.76
    oa̍t
    -0.75
    httphttps
    -0.74
    ftagPool
    -0.71
    MemoryWarning
    -0.70
    POSITIVE LOGITS
     and
    0.35
     due
    0.29
     or
    0.28
     Lingkungan
    0.28
     empfohlen
    0.28
     Studium
    0.28
     redus
    0.27
    時
    0.27
    ↵
    0.27
     but
    0.26
    Activations Density 0.027%

    No Known Activations