© 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. 0-GEMMASCOPE-RES-16K
    11. 7125
    Prev
    Next
    INDEX
    Explanations

    sections related to summaries and detailed descriptions of research findings and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     information
    -0.77
     results
    -0.72
     description
    -0.69
     use
    -0.66
     analysis
    -0.66
     explanation
    -0.64
     knowledge
    -0.64
     data
    -0.63
     experience
    -0.63
     response
    -0.63
    POSITIVE LOGITS
     Preparation
    1.21
     Calculation
    1.19
     Requirements
    1.15
     Approval
    1.13
     Results
    1.11
     Prediction
    1.10
     Details
    1.09
     Requirement
    1.09
     Comparison
    1.09
     Procedure
    1.08
    Activations Density 0.874%

    No Known Activations