© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12213
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to messiness or being dirty

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

    soiled or dirty state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.62
    IsMutable
    -0.54
     '\\;'
    -0.54
     createContext
    -0.50
    enderror
    -0.50
     DBNull
    -0.50
     defStyleAttr
    -0.47
    AnimationsModule
    -0.47
    دانشنامهٔ
    -0.46
    商品説明
    -0.46
    POSITIVE LOGITS
     dirty
    1.13
     dirt
    1.03
     soiled
    1.01
     muddy
    1.00
    dirty
    0.96
    dirt
    0.88
     Dirty
    0.86
     wet
    0.86
     mud
    0.85
     Dirt
    0.84
    Activations Density 0.043%

    No Known Activations