© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2409
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical systems and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Table
    -0.64
     anymore
    -0.62
     irgendwie
    -0.59
     voyez
    -0.57
     apapun
    -0.57
     anyway
    -0.55
    Anyway
    -0.55
     Anything
    -0.55
     Figure
    -0.55
     anything
    -0.55
    POSITIVE LOGITS
     novel
    0.73
     demonstrate
    0.69
     Implications
    0.66
     demonstrates
    0.64
     demonstrating
    0.61
    illust
    0.60
     erstmals
    0.60
     implications
    0.60
    novel
    0.57
     show
    0.57
    Activations Density 1.353%

    No Known Activations