© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2588
    Prev
    Next
    INDEX
    Explanations

    information related to mold prevention and management

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

    Mold, radon, structural issues, and water damage in homes

    np_acts-logits-general · gemini-2.0-flash

    building moisture and structural damage

    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
    ArgumentParser
    -0.72
    MemoryWarning
    -0.69
    UserScript
    -0.68
    rungsseite
    -0.67
    ViewFeatures
    -0.67
    
    -0.65
    ViewImports
    -0.64
    getSimpleName
    -0.64
    ImageContext
    -0.63
    hopped
    -0.62
    POSITIVE LOGITS
     structural
    1.02
    Structural
    0.86
     structurally
    0.86
     Structural
    0.84
     estructural
    0.84
    structural
    0.83
     leaks
    0.77
     mold
    0.76
     foundation
    0.73
     STRUCT
    0.73
    Activations Density 0.121%

    No Known Activations