© 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. 9668
    Prev
    Next
    INDEX
    Explanations

    syntactical elements and parameters in programming and configuration contexts

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

    Parameters, often enclosed in brackets or parentheses

    np_acts-logits-general · gemini-2.0-flash

    parameters and limits

    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
     Status
    -0.48
     Rankings
    -0.47
     Crocker
    -0.45
     lendemain
    -0.45
     getStatus
    -0.45
    Timmy
    -0.45
    Status
    -0.44
    getStatus
    -0.44
    Palmarès
    -0.43
    attled
    -0.43
    POSITIVE LOGITS
     max
    0.97
    tagHelperRunner
    0.97
     tolerance
    0.87
    GEBURTSDATUM
    0.86
    max
    0.83
     step
    0.83
     minimum
    0.83
     threshold
    0.83
     Max
    0.82
     limit
    0.81
    Activations Density 0.690%

    No Known Activations