© 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. 994
    Prev
    Next
    INDEX
    Explanations

    patterns of academic research objectives and study purposes

    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
     anunci
    -0.33
    GetAxis
    -0.33
    Announcements
    -0.33
     anuncia
    -0.33
     pazi
    -0.32
     announcing
    -0.32
    announcement
    -0.31
    announce
    -0.31
     announcement
    -0.31
     Glaubens
    -0.31
    POSITIVE LOGITS
     investigate
    1.85
     examine
    1.78
     examined
    1.73
     investigates
    1.73
     examining
    1.72
     investigated
    1.70
     explore
    1.70
     investigating
    1.68
     examination
    1.65
     investigation
    1.64
    Activations Density 1.641%

    No Known Activations