© 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. 24-GEMMASCOPE-RES-16K
    11. 4933
    Prev
    Next
    INDEX
    Explanations

    elements related to gardens and outdoor facilities

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

    after commas

    np_acts-logits-general · gemini-2.0-flash

    garden structures and features

    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
     HasFactory
    -0.67
    UserScript
    -0.66
     MainAxisSize
    -0.63
    RegressionTest
    -0.62
    DebuggerNonUser
    -0.59
    makeConstraints
    -0.57
    RegistryLite
    -0.56
    sizeCache
    -0.54
    urlpatterns
    -0.54
    dataclass
    -0.54
    POSITIVE LOGITS
     paths
    0.71
     swings
    0.70
     path
    0.66
     swing
    0.66
     perg
    0.65
     flower
    0.64
     gazebo
    0.62
     shed
    0.60
     pergola
    0.59
     fountain
    0.59
    Activations Density 0.131%

    No Known Activations