© 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. 18-GEMMASCOPE-RES-16K
    11. 4405
    Prev
    Next
    INDEX
    Explanations

    parameters and their definitions within a programming context

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

    "param"

    np_acts-logits-general · gemini-2.0-flash

    JSDoc parameter tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.71
     فريبيس
    -0.65
     itſelf
    -0.64
     '\\;'
    -0.61
    readdir
    -0.61
    Condol
    -0.61
    Havolalar
    -0.60
    SharedDtor
    -0.59
     poffe
    -0.59
     clearColor
    -0.59
    POSITIVE LOGITS
    param
    1.19
    PARAM
    0.83
     param
    0.81
     {*}
    0.75
    </u>
    0.74
    </strong>
    0.73
    hdashline
    0.71
     params
    0.69
     PARAM
    0.68
     Param
    0.67
    Activations Density 0.035%

    No Known Activations