© 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. 42233
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Murphy."

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

    Murphy

    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
    /**
    -0.61
    揄
    -0.58
    جوايز
    -0.53
    withIdentifier
    -0.50
    onedDateTime
    -0.49
    mtd
    -0.47
    BASELINE
    -0.47
     TextAlign
    -0.47
    er
    -0.46
    躇
    -0.46
    POSITIVE LOGITS
     Murphy
    1.16
    Murphy
    1.10
     Puppy
    0.54
    Kirby
    0.52
    PHY
    0.52
    université
    0.50
    phy
    0.49
     producti
    0.49
     Sunshine
    0.48
    __).
    0.48
    Activations Density 0.002%

    No Known Activations