© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102619
    Prev
    Next
    INDEX
    Explanations

    key terms related to historical contexts and attributes of significant figures or events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Ruhe
    -0.36
     direta
    -0.33
     confirmación
    -0.32
     immediately
    -0.31
    ätigung
    -0.29
     perceived
    -0.29
    ním
    -0.29
     Rechnung
    -0.28
     Wahrnehmung
    -0.28
     íntegra
    -0.28
    POSITIVE LOGITS
     Infórmanos
    0.81
     AssemblyTitle
    0.68
    dafx
    0.67
     ProtoMessage
    0.66
    PreferredItem
    0.66
    ReusableCell
    0.65
    enterOuterAlt
    0.63
     يتيمه
    0.63
     كومونز
    0.62
    niſſe
    0.62
    Activations Density 0.092%

    No Known Activations