© 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. 4-GEMMASCOPE-RES-16K
    11. 1156
    Prev
    Next
    INDEX
    Explanations

    specific terms related to research, analysis, and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whole
    -0.55
     entire
    -0.53
    phemy
    -0.52
    cide
    -0.52
    原始内容存档
    -0.51
    sscanf
    -0.51
    asts
    -0.49
    tabolism
    -0.49
     content
    -0.49
     full
    -0.48
    POSITIVE LOGITS
    ImageContext
    0.74
     Meksiku
    0.71
     CreateTagHelper
    0.69
    ########.
    0.64
     comuniques
    0.64
     ویکی‌پدی
    0.60
     Cientí
    0.59
    CodeAttribute
    0.59
     estekak
    0.57
    Rohy
    0.57
    Activations Density 2.197%

    No Known Activations