© 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. 93
    Prev
    Next
    INDEX
    Explanations

    the word "about" and its variations

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

    about introductory phrases

    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
    tagHelperRunner
    -0.85
    GTCX
    -0.81
    ftagPool
    -0.71
     Normdatei
    -0.70
     estekak
    -0.69
    下载附件
    -0.68
     Taktlose
    -0.66
     FetchType
    -0.63
    Sucesor
    -0.59
    saraba
    -0.59
    POSITIVE LOGITS
    About
    0.62
     About
    0.58
     about
    0.52
     ABOUT
    0.49
    about
    0.48
     Acerca
    0.47
     Tentang
    0.45
    關於
    0.44
    ABOUT
    0.41
     description
    0.40
    Activations Density 0.001%

    No Known Activations