© 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. 20-GEMMASCOPE-RES-16K
    11. 1091
    Prev
    Next
    INDEX
    Explanations

    discussions about norms and rules that govern behavior, particularly in political contexts

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

    regulations or guidelines

    np_acts-logits-general · gemini-2.0-flash

    camp rules, court rules, policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ActionCreators
    -0.67
    extAlignment
    -0.64
     propOrder
    -0.64
    TextHelper
    -0.60
    \{\\
    -0.59
     تضيفلها
    -0.57
     Wikimedijinoj
    -0.56
     חיצוניים
    -0.56
    ########.
    -0.55
    Vidite
    -0.55
    POSITIVE LOGITS
     rules
    3.12
     Rules
    2.71
    rules
    2.69
     rule
    2.63
    Rules
    2.59
     RULES
    2.44
     Rule
    2.27
    rule
    2.26
    RULES
    2.25
    Rule
    2.16
    Activations Density 0.497%

    No Known Activations