© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13396
    Prev
    Next
    INDEX
    Explanations

    non-linear formatting and special characters in the text

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

    Text surrounded by brackets

    np_acts-logits-general · gemini-2.0-flash

    Xsan ()

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    -0.98
     surla
    -0.89
     snippetHide
    -0.87
    sizeCache
    -0.82
    GOTREF
    -0.82
    TagMode
    -0.79
    WebElementEntity
    -0.79
     transfieras
    -0.77
    новниш
    -0.76
    ConstraintMaker
    -0.76
    POSITIVE LOGITS
    !
    0.34
    作为
    0.32
     anymore
    0.29
    訊息
    0.28
     için
    0.28
    ↵↵
    0.28
     Hirst
    0.28
     suces
    0.28
    .
    0.28
     interesan
    0.26
    Activations Density 0.194%

    No Known Activations