© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 4011
    Prev
    Next
    INDEX
    Explanations

    references to classes and methods in programming, particularly within a specific context related to client and threading operations

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

    Fisher Scientific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "-",
    -0.50
     "")
    
    -0.48
    '])){
    
    -0.47
     camb
    -0.47
     muse
    -0.47
    雳
    -0.46
     $\}$
    -0.45
    folium
    -0.45
    }")
    
    -0.45
     balancer
    -0.45
    POSITIVE LOGITS
    GEBURTS
    0.89
    ISupport
    0.73
    Xna
    0.68
    posables
    0.67
    ThreadPool
    0.65
    npj
    0.61
    tainted
    0.56
    getColumn
    0.55
     infierno
    0.54
    ToScroll
    0.50
    Activations Density 0.004%

    No Known Activations