© 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. 83886
    Prev
    Next
    INDEX
    Explanations

    references to legislative bodies and assemblies

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

    legislative assemblies

    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
    </tfoot>
    -0.46
    Pete
    -0.45
     مرئيه
    -0.43
     localVar
    -0.42
     sûr
    -0.40
     końca
    -0.40
     mexicano
    -0.40
    Colin
    -0.39
     verdades
    -0.39
    Fred
    -0.38
    POSITIVE LOGITS
     Assembly
    1.16
     assembly
    0.93
    Assembly
    0.88
     ASSEMBLY
    0.84
     Assemblies
    0.81
     assemblies
    0.74
    EMBLY
    0.72
    sembly
    0.72
     Assemb
    0.71
    assembly
    0.70
    Activations Density 0.006%

    No Known Activations