© 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. 6286
    Prev
    Next
    INDEX
    Explanations

    legal and contractual language, particularly around warranties and obligations

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

    "Mercury"

    np_acts-logits-general · gemini-2.0-flash

    Mercury company/brand

    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
     Kato
    -0.68
    endphp
    -0.65
     SSP
    -0.62
     BX
    -0.60
     Coolidge
    -0.60
     Bani
    -0.60
     Lausanne
    -0.60
     Johnstone
    -0.58
     Heli
    -0.58
     Nagpur
    -0.58
    POSITIVE LOGITS
     MER
    2.52
    Mer
    2.38
     Mer
    2.35
     mer
    2.26
    MER
    2.21
     MERC
    2.09
    mer
    2.03
     Merc
    1.95
     Mercer
    1.92
     merc
    1.81
    Activations Density 0.223%

    No Known Activations