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. 20-GEMMASCOPE-RES-131K
    6. 16887
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to lattice structures and percolation theory

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

    square lattice

    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
     financiero
    -0.37
     przys
    -0.36
    ẨM
    -0.36
     geçmiş
    -0.35
     violación
    -0.34
     commissioned
    -0.34
    cerrar
    -0.33
     nonUne
    -0.33
    eradish
    -0.33
     financieras
    -0.33
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.60
    MLLoader
    0.51
     Hop
    0.47
     hopping
    0.45
     Random
    0.44
     चीज़ों
    0.43
    feu
    0.42
     الحره
    0.42
    ectady
    0.42
     tấm
    0.42
    Activations Density 0.271%

    No Known Activations