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

    Neuronpedia

    Jacobian LensNEW
    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. 65441
    Prev
    Next
    INDEX
    Explanations

    Japanese verbs reflecting ongoing actions or states

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

    verb continuative forms

    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
    もしれません
    -0.54
     Romains
    -0.49
    来ました
    -0.49
     Grecs
    -0.48
    ตำ
    -0.48
     vacancy
    -0.48
    Fau
    -0.47
     personeel
    -0.47
     fotografico
    -0.47
     olmayan
    -0.47
    POSITIVE LOGITS
    して
    0.70
    めて
    0.66
    んで
    0.66
    げて
    0.61
    RegressionTest
    0.60
    って
    0.59
    えて
    0.58
    て
    0.58
    脚注の使い方
    0.57
    で
    0.56
    Activations Density 0.007%

    No Known Activations