© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 57106
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational and structural changes

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

    former, independent, breakaway states

    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
     AssemblyCulture
    -0.57
     '\\;'
    -0.52
    IVEREF
    -0.47
     quieras
    -0.43
     contenir
    -0.42
     tocó
    -0.42
     torebka
    -0.42
     enfans
    -0.42
     vloer
    -0.41
     pemasangan
    -0.41
    POSITIVE LOGITS
     former
    0.51
     independ
    0.51
     independent
    0.51
    独立
    0.48
     autonomy
    0.47
     renegade
    0.46
     breakaway
    0.46
     Former
    0.45
     diss
    0.43
    independent
    0.42
    Activations Density 0.107%

    No Known Activations