© 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. 10913
    Prev
    Next
    INDEX
    Explanations

    phrases that express actions or intentions related to trying, playing, and using tools or methods

    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
    PostInfinity
    -0.47
     biais
    -0.33
    Rohy
    -0.29
    تاح
    -0.27
    جمعیت
    -0.26
     Ilustra
    -0.26
    
    -0.26
     Clippers
    -0.26
     chó
    -0.26
     cámara
    -0.25
    POSITIVE LOGITS
     experimenting
    1.81
     experimentation
    1.73
     messing
    1.68
     experiment
    1.67
    Experiment
    1.63
     Experiment
    1.63
     tinkering
    1.60
    experiment
    1.58
     experimented
    1.55
     tinker
    1.47
    Activations Density 0.489%

    No Known Activations