© 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. 22-GEMMASCOPE-RES-16K
    11. 12634
    Prev
    Next
    INDEX
    Explanations

    references to systems and methods in a technical context

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

    "system" or "systems"

    np_acts-logits-general · gemini-2.0-flash

    systematics and applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.95
     ſeveral
    -0.94
     שוליים
    -0.93
     himſelf
    -0.84
     Efq
    -0.84
     Jefus
    -0.82
     feveral
    -0.81
     Monfieur
    -0.79
     Chrift
    -0.77
    sidemargin
    -0.77
    POSITIVE LOGITS
     systems
    1.20
     Systems
    1.03
     SYSTEMS
    0.94
     system
    0.88
    systems
    0.87
    atics
    0.87
    wide
    0.86
    atically
    0.85
    Systems
    0.85
     System
    0.83
    Activations Density 0.115%

    No Known Activations