© 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. 78193
    Prev
    Next
    INDEX
    Explanations

    structured data elements, particularly items and dictionary entries

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

    single, unique, only

    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
     gyhoeddwyd
    -0.43
    aua
    -0.37
    懋
    -0.36
    melse
    -0.36
    跆
    -0.35
     Horner
    -0.35
    ตน
    -0.35
     calendriers
    -0.34
    zera
    -0.34
    ELTS
    -0.34
    POSITIVE LOGITS
     einzigen
    0.61
    Personendaten
    0.57
    唯一的
    0.55
    etlen
    0.55
    interopRequire
    0.55
    只有一个
    0.54
     ujednoznacz
    0.52
     estekak
    0.50
     tunggal
    0.50
     einzige
    0.50
    Activations Density 0.338%

    No Known Activations