© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9992
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to policies, rules, and exceptions within frameworks or governance structures

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

    "rule" or "rules"

    np_acts-logits-general · gemini-2.0-flash

    general rule

    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
     GenerationType
    -0.59
     estimés
    -0.57
    thâu
    -0.54
     MainAxisSize
    -0.52
    äsident
    -0.48
    Espèce
    -0.47
     îmb
    -0.47
    includegraphics
    -0.47
     préféré
    -0.45
    entennial
    -0.45
    POSITIVE LOGITS
     rule
    4.35
    rule
    3.89
     Rule
    3.85
    Rule
    3.70
     RULE
    3.48
     rules
    3.40
    RULE
    3.12
     Rules
    3.11
    rules
    3.05
    Rules
    2.90
    Activations Density 0.301%

    No Known Activations