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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 7942
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computational modeling and fluid dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ladri
    -0.63
     titolata
    -0.59
    bezpiecz
    -0.58
     carico
    -0.58
     settimane
    -0.56
     déposer
    -0.55
     preſent
    -0.55
     giusti
    -0.54
     Activate
    -0.54
     découver
    -0.54
    POSITIVE LOGITS
     simulation
    0.74
     modelling
    0.73
     modeling
    0.72
     simulations
    0.72
     calculations
    0.70
     model
    0.64
     calculation
    0.63
     simulating
    0.61
     analysis
    0.61
     mxArray
    0.60
    Activations Density 1.104%

    No Known Activations