Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 69337
    Prev
    Next
    INDEX
    Explanations

    references to system-related processes and functions in programming or technical contexts

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

    system and syscalls

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AndEndTag
    -0.33
     صوتيه
    -0.33
    addTab
    -0.33
    SupportActionBar
    -0.32
    WithMany
    -0.31
    JMenu
    -0.31
     begrü
    -0.30
    IRQn
    -0.29
    addGap
    -0.29
    Ro
    -0.29
    POSITIVE LOGITS
    system
    3.02
     system
    2.31
    SYSTEM
    2.14
     SYSTEM
    2.13
    ystem
    2.05
    systems
    2.03
    System
    2.02
     sistem
    1.99
    系统
    1.88
    sistem
    1.86
    Activations Density 0.014%

    No Known Activations