Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6636
    Prev
    Next
    INDEX
    Explanations

    references to cycles, particularly in various contexts such as nature, economics, and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.80
     igång
    -0.80
     quelcon
    -0.78
     aveug
    -0.78
     fédé
    -0.77
     Dux
    -0.76
    engertian
    -0.75
    ReusableCell
    -0.73
     copertina
    -0.73
     malheure
    -0.72
    POSITIVE LOGITS
     cycle
    1.43
     Cycle
    1.24
     cycles
    1.11
    Cycle
    1.11
     CYCLE
    1.09
    cycle
    1.09
     Cycles
    0.91
     cyclic
    0.86
     ciclo
    0.82
    Loop
    0.80
    Activations Density 0.096%

    No Known Activations