© 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. 20-GEMMASCOPE-RES-16K
    6. 688
    Prev
    Next
    INDEX
    Explanations

    terms related to systems and their functionality in various contexts

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

    "system"

    np_acts-logits-general · gemini-2.0-flash

    system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omitempty
    -0.56
    PreferredItem
    -0.54
    bcryptjs
    -0.52
    
    -0.51
     Nullable
    -0.48
     adv
    -0.47
     ADV
    -0.46
    listdir
    -0.45
    PositiveButton
    -0.45
    Fug
    -0.44
    POSITIVE LOGITS
     system
    1.02
     système
    0.96
     systeem
    0.95
     sistema
    0.93
    ssystem
    0.89
     systems
    0.82
     sistemas
    0.82
     sistem
    0.81
     systému
    0.81
    系统
    0.81
    Activations Density 0.714%

    No Known Activations