© 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. 10457
    Prev
    Next
    INDEX
    Explanations

    instances of user interface components related to displaying information or prompts

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

    Empty states or disabled states of UI elements

    np_acts-logits-general · gemini-2.0-flash

    programming source code and markup

    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
     labor
    -0.45
    JoinTable
    -0.42
    callee
    -0.42
    obenz
    -0.40
     mật
    -0.39
    RegressionTest
    -0.38
     ली
    -0.37
     kohdetta
    -0.36
     Computational
    -0.36
    labor
    -0.36
    POSITIVE LOGITS
    basicConfig
    0.54
    parsedMessage
    0.48
    Diweddarwch
    0.47
     Wikimedijinoj
    0.47
    optionalTypeArgs
    0.45
    ThroughAttribute
    0.45
     forState
    0.42
     propOrder
    0.41
    StoreMessageInfo
    0.41
    帖最后由
    0.41
    Activations Density 0.271%

    No Known Activations