© 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. 83296
    Prev
    Next
    INDEX
    Explanations

    terms related to formal and informal status or regulations

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

    unofficial, informal, de facto

    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
     dům
    -0.41
     completely
    -0.39
     řízení
    -0.34
     völlig
    -0.33
    진
    -0.33
    SelectedValue
    -0.32
     incapa
    -0.32
    onomía
    -0.32
     třeba
    -0.32
    dificio
    -0.32
    POSITIVE LOGITS
     unofficial
    1.80
     informally
    1.13
     informal
    1.09
    Informal
    1.02
     Informal
    0.99
     impromptu
    0.73
     unwritten
    0.70
     makeshift
    0.70
    parsedMessage
    0.67
     uLocal
    0.66
    Activations Density 0.010%

    No Known Activations