© 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. 31-GEMMASCOPE-RES-16K
    11. 15747
    Prev
    Next
    INDEX
    Explanations

    references to software installation and server management issues

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

    technical code, server configuration, and programming syntax references.

    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
    ConstraintMaker
    -0.45
    Palmarès
    -0.38
     виправивши
    -0.36
    ImageContext
    -0.35
    jsxFileName
    -0.35
     Parcelable
    -0.34
    🇶
    -0.34
    etcode
    -0.34
    jabi
    -0.34
     DNI
    -0.33
    POSITIVE LOGITS
     server
    1.16
     Server
    1.02
    server
    0.98
    Server
    0.94
    createServer
    0.91
     servers
    0.89
     servidor
    0.87
     listening
    0.86
     Listening
    0.85
     serveur
    0.85
    Activations Density 0.482%

    No Known Activations