© 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. 12-GEMMASCOPE-RES-16K
    6. 1391
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of confusion or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.70
    Aholisi
    -0.54
    脚注の使い方
    -0.52
     ambientale
    -0.50
    ValueStyle
    -0.50
     nahilalakip
    -0.50
     autorytatywna
    -0.48
    loroethene
    -0.47
    Personensuche
    -0.46
    ArrowToggle
    -0.45
    POSITIVE LOGITS
    makeConstraints
    0.46
    fjspx
    0.45
     why
    0.43
     varför
    0.38
     pourquoi
    0.38
     wtf
    0.37
     Wtf
    0.36
     waarom
    0.35
    Wtf
    0.35
     Justice
    0.35
    Activations Density 0.318%

    No Known Activations