© 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. 102765
    Prev
    Next
    INDEX
    Explanations

    elements related to responses and quiz answers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    References to incorrect or wrong answers in code for a quiz application, including variables, methods, and XML elements containing terms like "bad", "mauvaise", or variations in both English and French.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     initComponents
    -0.32
    λών
    -0.32
     skolen
    -0.31
     cí
    -0.31
     Allí
    -0.30
     proposte
    -0.30
    jualan
    -0.30
     analogous
    -0.30
    licence
    -0.29
    ┤
    -0.29
    POSITIVE LOGITS
    WebElementEntity
    0.59
     Chwiliwch
    0.53
    ğraf
    0.53
    انجليز
    0.52
     useAppContext
    0.51
    sidemargin
    0.50
    tanleria
    0.50
    ↹
    0.49
     <=",
    0.48
     Administrativna
    0.48
    Activations Density 0.022%

    No Known Activations