© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 5516
    Prev
    Next
    INDEX
    Explanations

    words related to "st" as a prefix, particularly in medical or anatomical contexts

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

    words starting with st

    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
    
    -0.86
    extAlignment
    -0.70
     للمعارف
    -0.67
    PyExc
    -0.66
     glyphicon
    -0.65
     سكانية
    -0.64
    sizeCache
    -0.63
    CloseOperation
    -0.62
    HomeAsUpEnabled
    -0.62
    Dichloropropane
    -0.61
    POSITIVE LOGITS
     st
    2.27
    St
    1.23
    st
    1.21
     ST
    1.20
     St
    1.14
    ST
    1.07
     Stur
    0.90
     स्ट
    0.90
     stent
    0.89
     ст
    0.84
    Activations Density 0.004%

    No Known Activations