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

    Neuronpedia

    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. 9-GEMMASCOPE-RES-131K
    11. 17295
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dies" in various forms

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

    crafting dies or death

    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
    存于互联网档案馆
    -0.63
     المعيارى
    -0.61
     fhort
    -0.59
    DataAnnotations
    -0.58
     Efq
    -0.55
     MTL
    -0.55
     Arp
    -0.55
    granate
    -0.54
    [@
    -0.54
    Swal
    -0.53
    POSITIVE LOGITS
     Dies
    1.80
    Dies
    1.66
     dies
    1.63
     DIES
    1.34
    dies
    1.20
     muere
    0.66
     Diesel
    0.60
     diesel
    0.60
    Diesel
    0.55
    diesel
    0.52
    Activations Density 0.007%

    No Known Activations