© 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. 44066
    Prev
    Next
    INDEX
    Explanations

    details related to personal identification and legal documentation

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

    Azumi, incident, time

    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
     estekak
    -0.74
    expandindo
    -0.59
     चीज़ों
    -0.50
    Tembelea
    -0.50
    
    -0.49
     autorytatywna
    -0.47
    WriteTagHelper
    -0.47
    adaptiveStyles
    -0.46
    being
    -0.45
    BeginContext
    -0.45
    POSITIVE LOGITS
    서는
    1.31
     is
    1.24
     것은
    1.05
    는
    1.00
    리는
    0.96
    지는
    0.95
    は
    0.94
    에는
    0.94
     then
    0.92
     thì
    0.91
    Activations Density 0.037%

    No Known Activations