© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8622
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data processing and reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical code and programming syntax elements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Taktlose
    -0.47
     ModelExpression
    -0.42
     StatefulWidget
    -0.37
    новништво
    -0.37
     vectorielle
    -0.36
     trò
    -0.36
     placa
    -0.35
    setGravity
    -0.35
    pgterms
    -0.35
     réglable
    -0.35
    POSITIVE LOGITS
     Tableau
    0.82
     ETL
    0.75
     Analytics
    0.72
    Tableau
    0.70
     analytical
    0.68
     analytics
    0.68
     Hadoop
    0.67
     analytic
    0.67
     tableau
    0.65
     Analytical
    0.63
    Activations Density 0.592%

    No Known Activations