© 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 EvalsExportsAPI 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. 119830
    Prev
    Next
    INDEX
    Explanations

    instances of the word "runner" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Portail
    -0.61
    ymce
    -0.52
    <bos>
    -0.49
    addGap
    -0.48
    ig
    -0.46
    SuppressLint
    -0.45
    indexOf
    -0.43
    IG
    -0.42
     Garg
    -0.41
     Diaz
    -0.40
    POSITIVE LOGITS
     Runner
    1.45
     runner
    1.35
    Runner
    1.30
    runner
    1.22
     Runners
    1.13
     runners
    1.05
    Runners
    1.02
    runners
    0.98
    SpringRunner
    0.85
    TestRunner
    0.85
    Activations Density 0.003%

    No Known Activations