© 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. 34-GEMMASCOPE-RES-16K
    11. 11469
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Accent
    -0.30
     Young
    -0.29
     Bender
    -0.28
     beloved
    -0.28
    NORE
    -0.27
    ựng
    -0.27
     Bear
    -0.27
    SPIR
    -0.27
     bek
    -0.26
     Perry
    -0.26
    POSITIVE LOGITS
    httphttps
    0.75
     nahilalakip
    0.73
    richTextPanel
    0.72
     tartalomajánló
    0.70
     дописавши
    0.69
     Roskov
    0.68
    IVEREF
    0.67
     Wiktionnaire
    0.66
     defaultstate
    0.66
    
    0.65
    Activations Density 0.156%

    No Known Activations