© 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. 15913
    Prev
    Next
    INDEX
    Explanations

    references to specific legal rules and their applications

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

    rules or regulations

    np_acts-logits-general · gemini-2.0-flash

    rule identifiers

    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
    tagHelperRunner
    -0.69
    ")));
    -0.58
    "]);
    -0.55
    ENCIES
    -0.54
    )}</
    -0.54
    npy
    -0.52
    ihnachten
    -0.52
    HideFlags
    -0.52
    +</
    -0.52
    {\"
    -0.51
    POSITIVE LOGITS
     rules
    1.27
     Rules
    1.24
    rules
    1.13
    Rules
    1.09
     RULES
    1.08
     rule
    1.05
     Rule
    1.03
     RULE
    1.01
    RULES
    0.95
     reglas
    0.89
    Activations Density 0.124%

    No Known Activations