© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2481
    Prev
    Next
    INDEX
    Explanations

    calls to action encouraging readers to explore or check out additional content

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

    imperative verbs that invite the reader to take action or explore content (such as "Check," "Take," "Believe," "go," "get," "send," "click").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geografia
    -0.50
    parsedMessage
    -0.50
    Gön
    -0.50
    ConstraintMaker
    -0.48
    Clik
    -0.47
    bcryptjs
    -0.46
     />\
    -0.46
     gabbana
    -0.45
     CoreData
    -0.45
     itſelf
    -0.45
    POSITIVE LOGITS
     yourself
    0.90
     yourselves
    0.73
     your
    0.73
    ंदीखरीदारी
    0.70
     noDo
    0.66
     nahilalakip
    0.62
     Yourself
    0.57
    your
    0.56
    lah
    0.50
    你自己
    0.50
    Activations Density 0.553%

    No Known Activations