© 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. 2-GEMMASCOPE-RES-16K
    6. 9267
    Prev
    Next
    INDEX
    Explanations

    terms related to configurations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comfort
    -0.40
    
    -0.40
    rowser
    -0.39
     dure
    -0.38
     fat
    -0.38
    AxisAlignment
    -0.38
     wrath
    -0.37
    comfort
    -0.37
    ║
    -0.36
    Comfort
    -0.35
    POSITIVE LOGITS
     config
    1.52
    Config
    1.41
     Config
    1.38
    config
    1.20
    setConfig
    0.91
     conf
    0.90
     getConfig
    0.88
     configs
    0.88
    getConfig
    0.88
     CONFIG
    0.88
    Activations Density 0.080%

    No Known Activations