© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5887
    Prev
    Next
    INDEX
    Explanations

    phrases related to the performance and accuracy of models or systems

    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
    自己是
    -0.40
    Herzliche
    -0.33
    Географија
    -0.30
    HasOne
    -0.29
     الاطلاع
    -0.28
    
    -0.28
    msleep
    -0.28
    Читайте
    -0.28
    Géographie
    -0.27
    iske
    -0.26
    POSITIVE LOGITS
     desired
    2.09
     planned
    1.88
     requested
    1.88
    desired
    1.82
     intended
    1.79
     promised
    1.78
     specified
    1.75
     proposed
    1.75
     predicted
    1.72
     envisaged
    1.66
    Activations Density 1.367%

    No Known Activations