© 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. 24-GEMMASCOPE-RES-131K
    11. 1401
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating relationships or connections between entities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    continua et al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     resourceCulture
    -0.41
     serce
    -0.37
     serca
    -0.30
     najwięks
    -0.28
    URLException
    -0.28
     Auswirkungen
    -0.28
    достатки
    -0.27
     verksamhet
    -0.27
    Normdaten
    -0.26
     stället
    -0.26
    POSITIVE LOGITS
     etc
    0.88
    etc
    0.79
     Etc
    0.71
    endphp
    0.70
    +#+#
    0.65
    ⟬
    0.65
     ETC
    0.60
     ועוד
    0.60
    Etc
    0.58
     Infórmanos
    0.58
    Activations Density 0.055%

    No Known Activations