© 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. 24-GEMMASCOPE-RES-16K
    6. 7658
    Prev
    Next
    INDEX
    Explanations

    specific items or collectibles in a game context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    video games or the Sims

    np_acts-logits-general · gemini-2.0-flash

    video game genres

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.71
     InputDecoration
    -0.62
    ViewImports
    -0.59
     initWithFrame
    -0.58
     Kyiv
    -0.58
    Pyx
    -0.58
    AnimationsModule
    -0.57
     protoimpl
    -0.56
     Tripoli
    -0.55
    Jereo
    -0.54
    POSITIVE LOGITS
     Sims
    1.15
     sims
    1.10
    Sims
    1.02
    sims
    1.01
     Sim
    0.98
     sim
    0.91
    Sim
    0.90
    sim
    0.80
    SIM
    0.69
     EA
    0.67
    Activations Density 0.042%

    No Known Activations