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. 45823
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Th" and its variations, typically related to T-helper cells in immunology

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

    words starting with Th

    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
     سكانية
    -0.68
     незавершена
    -0.66
    Hozzáférés
    -0.65
    ezy
    -0.61
    `;
    
    -0.57
    éez
    -0.56
    ("")]
    
    -0.55
    apes
    -0.55
    eté
    -0.54
    oyun
    -0.54
    POSITIVE LOGITS
     Th
    2.19
    Th
    1.91
     th
    1.41
     TH
    1.30
    TH
    0.99
     THR
    0.93
    th
    0.91
     Thra
    0.88
     Ph
    0.85
     Tho
    0.83
    Activations Density 0.013%

    No Known Activations