© 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 - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 12203
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Lewis" and related terms, with a focus on delays in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.66
     jScrollPane
    -0.65
     plufieurs
    -0.60
     Bewußt
    -0.60
     Schluß
    -0.60
     Füßen
    -0.58
     Wikiseite
    -0.57
     miniaturka
    -0.55
    colgante
    -0.54
     maioria
    -0.54
    POSITIVE LOGITS
    describe
    0.60
    xb
    0.60
     demonstrate
    0.54
     Explain
    0.54
    izi
    0.54
    createClass
    0.52
     exp
    0.52
     prove
    0.52
    define
    0.52
     []:
    0.50
    Activations Density 0.301%

    No Known Activations