© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13564
    Prev
    Next
    INDEX
    Explanations

    technical specifications and performance metrics related to computing devices

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

    performance or optimization

    np_acts-logits-general · gemini-2.0-flash

    computer performance and speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.71
     surla
    -0.62
    findpost
    -0.60
    deelte
    -0.60
    :✨
    -0.58
    ElementException
    -0.55
    ⓧ
    -0.54
     foncé
    -0.52
     Siren
    -0.52
     émotion
    -0.50
    POSITIVE LOGITS
     performance
    1.27
     CPU
    1.23
     Performance
    1.13
    Performance
    1.08
    performance
    1.08
     bottleneck
    1.02
     PERFORMANCE
    0.99
     latency
    0.98
     speed
    0.97
    CPU
    0.97
    Activations Density 0.799%

    No Known Activations