© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6535
    Prev
    Next
    INDEX
    Explanations

    terms related to operating system signals and errors

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

    CPU instructions and exceptions

    np_acts-logits-general · gemini-2.0-flash

    CPU memory faults and exceptions

    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
    ConstraintMaker
    -0.69
    rungsseite
    -0.53
    enumi
    -0.48
     dried
    -0.46
     NSCoder
    -0.43
     strum
    -0.43
     tvor
    -0.43
    IBOutlet
    -0.42
     repeated
    -0.42
     solstice
    -0.41
    POSITIVE LOGITS
    ImageContext
    0.71
     interrupt
    0.70
     betweenstory
    0.69
     interrupts
    0.67
     priority
    0.67
     Priority
    0.66
     MonoBehaviour
    0.66
    ruptedException
    0.65
     Walkover
    0.64
     Priorities
    0.64
    Activations Density 0.735%

    No Known Activations