© 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. 31-GEMMASCOPE-RES-131K
    11. 69578
    Prev
    Next
    INDEX
    Explanations

    references to the word "sting" and its related forms, particularly in the context of sting rays

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

    sting, stingray, Stinger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.59
    IVEREF
    -0.59
    richTextPanel
    -0.58
    contentLoaded
    -0.57
     HasFactory
    -0.56
    Personendaten
    -0.54
     nahilalakip
    -0.54
    Portail
    -0.53
     חיצוניים
    -0.52
     viewDidLoad
    -0.52
    POSITIVE LOGITS
     Sting
    0.84
    Sting
    0.80
     sting
    0.79
    sting
    0.65
     stings
    0.57
     Scorpion
    0.50
    corpion
    0.49
     stung
    0.49
     stinging
    0.48
    rays
    0.48
    Activations Density 0.005%

    No Known Activations