© 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. 1540
    Prev
    Next
    INDEX
    Explanations

    references to a person named Wilson, especially in relation to legal matters or drug transactions

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

    proper names, specifically the name "Wilson" appearing throughout legal case documents.

    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
    <h3>
    -0.47
    <em>
    -0.45
    <h2>
    -0.44
     Juz
    -0.37
     pocz
    -0.36
    an
    -0.32
     Quels
    -0.32
     sterben
    -0.32
    er
    -0.31
    Lle
    -0.31
    POSITIVE LOGITS
    Personensuche
    0.75
    ValueStyle
    0.73
    󠁮
    0.64
     defStyleAttr
    0.64
    ViewImports
    0.63
    ◓
    0.63
     للاسماء
    0.63
    FlatAppearance
    0.62
    
    0.62
     kaarangay
    0.58
    Activations Density 1.483%

    No Known Activations