Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 103188
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Cruz"

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

    Ted Cruz and Santa Cruz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.41
     fundamentales
    -0.39
    issionais
    -0.39
    shadowOffset
    -0.38
     définiti
    -0.37
    photobucket
    -0.37
     Witte
    -0.36
     redonde
    -0.36
    شنبه
    -0.36
     húmedo
    -0.36
    POSITIVE LOGITS
     Cruz
    2.55
    Cruz
    2.41
     CRUZ
    2.05
    cruz
    1.80
     cruz
    1.71
     Croix
    1.01
     Cross
    1.01
     CROSS
    0.98
     Kreuz
    0.95
     Cruise
    0.92
    Activations Density 0.001%

    No Known Activations