© 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. 16-GEMMASCOPE-RES-16K
    11. 8274
    Prev
    Next
    INDEX
    Explanations

    references to experimental procedures and actions taken in scientific contexts

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

    preceding "in", "at", "by", or "to"

    np_acts-logits-general · gemini-2.0-flash

    actions performed or conducted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     municipales
    -0.50
     المعيارى
    -0.46
    mobileqq
    -0.45
    ‌اند
    -0.44
    rohr
    -0.43
     étrangères
    -0.42
    做事
    -0.42
    blower
    -0.42
    Története
    -0.41
    ในการ
    -0.41
    POSITIVE LOGITS
     للمعارف
    0.78
    ="#"><
    0.78
    (!__
    0.74
    UnusedPrivate
    0.70
     involving
    0.69
     naught
    0.69
    parsedMessage
    0.67
    mybatisplus
    0.66
    LookAnd
    0.64
    RTEE
    0.64
    Activations Density 0.740%

    No Known Activations