© 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. 39-GEMMASCOPE-RES-16K
    11. 3009
    Prev
    Next
    INDEX
    Explanations

    references to specific football players and their performances or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.51
    tangentMode
    -0.49
    EndProject
    -0.47
     <>",
    -0.46
    ConstraintMaker
    -0.44
    Batis
    -0.44
    sizeCache
    -0.43
    出版年
    -0.43
    putan
    -0.42
    
    -0.42
    POSITIVE LOGITS
     scored
    0.52
     blessé
    0.48
     jugó
    0.45
     scorer
    0.44
     substitute
    0.43
     scoring
    0.43
     Injured
    0.43
    Goals
    0.43
     pemain
    0.41
     played
    0.40
    Activations Density 0.126%

    No Known Activations