© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13638
    Prev
    Next
    INDEX
    Explanations

    references to specific names or titles, specifically related to people or entities associated with "Wool" in various contexts

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

    author names and surnames in academic citations and bibliographic references.

    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
     linkovi
    -0.37
    
    -0.36
     Efe
    -0.36
    ẩy
    -0.35
    anair
    -0.35
     autorytatywna
    -0.35
    ➩
    -0.35
     palet
    -0.34
     Industri
    -0.34
     satisfy
    -0.33
    POSITIVE LOGITS
    AndEndTag
    0.67
     Woo
    0.55
    Woo
    0.55
     WO
    0.54
    ValueGeneration
    0.53
    Wo
    0.52
    ContentLoaded
    0.52
    NameInMap
    0.51
     Wo
    0.51
    XmlType
    0.50
    Activations Density 0.118%

    No Known Activations