© 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. 9-GEMMASCOPE-RES-131K
    11. 83184
    Prev
    Next
    INDEX
    Explanations

    instances of the word "document" and its variants, indicating a focus on documentation or written records

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

    documenting facts or evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     smě
    -0.48
    OpenHelper
    -0.47
    AccessFile
    -0.45
     financeiro
    -0.45
     bribe
    -0.45
    ranch
    -0.45
     astuces
    -0.44
    tinyos
    -0.42
    itespace
    -0.41
    Enllaços
    -0.41
    POSITIVE LOGITS
     documenting
    1.25
     documented
    1.16
    documented
    1.10
     documentation
    0.91
     documenta
    0.90
     dokument
    0.83
     dokumenti
    0.83
    Documented
    0.80
     document
    0.79
     Document
    0.78
    Activations Density 0.017%

    No Known Activations