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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28367
    Prev
    Next
    INDEX
    Explanations

    references to durations or time periods

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

    duration in the past

    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
     חיצוניים
    -0.94
     للمعارف
    -0.84
     TestBed
    -0.74
     termica
    -0.73
     springfox
    -0.73
     acrylique
    -0.72
     RSSSF
    -0.71
    DotNetBar
    -0.71
     utafitiHapana
    -0.71
     فريبيس
    -0.69
    POSITIVE LOGITS
     few
    0.62
     
    0.61
     version
    0.58
     ten
    0.56
    govina
    0.54
     te
    0.53
     four
    0.51
     five
    0.48
     three
    0.48
    PerformLayout
    0.47
    Activations Density 0.022%

    No Known Activations