© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13316
    Prev
    Next
    INDEX
    Explanations

    references to various types of devices

    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
    endphp
    -0.39
     constitución
    -0.37
     osobow
    -0.36
     general
    -0.36
     ILogger
    -0.35
     MainAxisSize
    -0.34
     Allgemeinen
    -0.34
     cementerio
    -0.34
     umum
    -0.33
    rimir
    -0.33
    POSITIVE LOGITS
     device
    3.02
     devices
    2.88
     Devices
    2.73
     Device
    2.67
     DEVICE
    2.44
    device
    2.38
    devices
    2.34
     DEVICES
    2.34
    Device
    2.27
    Devices
    2.27
    Activations Density 0.109%

    No Known Activations