© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 49633
    Prev
    Next
    INDEX
    Explanations

    the concept of excuses and justifications

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

    excuse and follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     goederen
    -0.41
    <em>
    -0.40
     independently
    -0.39
     Mawr
    -0.39
     bordada
    -0.38
    ButtonModule
    -0.37
    prav
    -0.36
    はじめに
    -0.36
    ModelMap
    -0.36
    brandt
    -0.35
    POSITIVE LOGITS
     excuses
    1.17
     excuse
    1.16
    excuse
    1.16
     Excuse
    1.01
    Excuse
    1.01
     excus
    0.95
     excused
    0.85
    cuses
    0.84
     alibi
    0.70
     excu
    0.68
    Activations Density 0.006%

    No Known Activations