© 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. 20-GEMMASCOPE-RES-131K
    11. 58975
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mohammed" or its variations

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

    Prophet Muhammad names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSlice
    -0.54
     Wikiseite
    -0.49
    lewati
    -0.49
    Conteúdo
    -0.45
     ältere
    -0.45
    ̈́
    -0.43
     kühl
    -0.43
     Rücksicht
    -0.42
     ddelweddau
    -0.42
     garantías
    -0.42
    POSITIVE LOGITS
     Mohammed
    0.98
    Mohammed
    0.91
     Muhammad
    0.89
     Mohammad
    0.89
     Muhammed
    0.87
    Mohammad
    0.86
    Muhammad
    0.81
    hammed
    0.80
     Mohamed
    0.76
    hammad
    0.74
    Activations Density 0.003%

    No Known Activations