© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29364
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols, likely related to formatting or references

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

    reader after specific code/math

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ện
    -0.56
     BorderRadius
    -0.54
     service
    -0.52
     Leg
    -0.50
    ع
    -0.49
    Tazama
    -0.48
    عم
    -0.48
     all
    -0.48
    tav
    -0.48
    get
    -0.47
    POSITIVE LOGITS
    ThroughAttribute
    0.85
    <0x00>
    0.82
     الفلك
    0.77
    出版年
    0.76
    fjspx
    0.72
    UserScript
    0.72
    MENAFN
    0.68
    -------------</
    0.68
    FMC
    0.67
    ={`/
    0.66
    Activations Density 0.000%

    No Known Activations