© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 123203
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly variations of the name "Justin"

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

    people named Justin, Justine, or Kristen

    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
     CreateTagHelper
    -0.51
    setFlags
    -0.49
     []:
    -0.46
    setCode
    -0.45
    endphp
    -0.45
    HasAnnotation
    -0.45
     specchio
    -0.44
     modelAndView
    -0.44
     schlafen
    -0.43
    uertos
    -0.43
    POSITIVE LOGITS
     Justin
    1.05
    Justin
    0.94
    justin
    0.91
     justin
    0.83
     Justine
    0.73
    jst
    0.68
     JUST
    0.67
     Timberlake
    0.65
     JT
    0.63
     Bieber
    0.62
    Activations Density 0.002%

    No Known Activations