© 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. 122759
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to processes and progression

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

    in the process becomes

    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
     TextInputType
    -0.62
     tunggu
    -0.53
     sür
    -0.48
     brancas
    -0.48
     publique
    -0.48
     supérieurs
    -0.48
     plufieurs
    -0.46
     defaultstate
    -0.46
     prochaine
    -0.45
    keur
    -0.45
    POSITIVE LOGITS
    Dabei
    0.67
     dabei
    0.65
     Dabei
    0.63
     frattempo
    0.54
     incidentally
    0.46
    ruptedException
    0.40
     resourceCulture
    0.38
     góp
    0.38
     daarbij
    0.38
    וך
    0.36
    Activations Density 0.012%

    No Known Activations