© 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. 2660
    Prev
    Next
    INDEX
    Explanations

    sentences and phrases related to schedules and time management

    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
     time
    -0.57
     late
    -0.51
    時
    -0.47
    брь
    -0.46
    gre
    -0.45
    tim
    -0.45
    stdc
    -0.44
     early
    -0.44
    sidemargin
    -0.43
    ital
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.81
    IUrlHelper
    0.78
     ویکی‌پدیا
    0.77
     viewDidLoad
    0.69
     виправивши
    0.66
    běh
    0.66
    expandindo
    0.65
    談社
    0.65
    erráneo
    0.64
     löyty
    0.64
    Activations Density 0.591%

    No Known Activations