© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5919
    Prev
    Next
    INDEX
    Explanations

    items and materials related to cleaning and hygiene

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

    cleaning or wiping

    np_acts-logits-general · gemini-2.0-flash

    cleaning and cleanup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.44
    بوابة
    -0.42
    Autoritní
    -0.38
    曜
    -0.38
     EDGE
    -0.38
     ligiloj
    -0.37
     autorytatywna
    -0.37
     rospy
    -0.37
    blockList
    -0.37
     Vorles
    -0.37
    POSITIVE LOGITS
     cleaning
    0.55
     nettoyer
    0.51
     clean
    0.50
     Clean
    0.47
     Cleaning
    0.47
     pulizia
    0.46
    MemoryWarning
    0.45
     cleaner
    0.45
     troubleshoot
    0.43
     nettoyage
    0.42
    Activations Density 0.293%

    No Known Activations