© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3370
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and consequences in various contexts

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

    Follows the word "to"

    np_acts-logits-general · gemini-2.0-flash

    to spur, limit, investigate, prevent

    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
     Efq
    -0.87
     itſelf
    -0.80
     myſelf
    -0.78
    Become
    -0.76
     Become
    -0.75
     become
    -0.72
     behaves
    -0.71
     iſt
    -0.70
     Jefus
    -0.69
     uſed
    -0.69
    POSITIVE LOGITS
     ensure
    0.60
     [*]
    0.52
    ″]
    0.51
    將
    0.47
     ensuring
    0.47
     CURIAM
    0.47
    ensure
    0.47
    ymce
    0.46
    "]),
    0.46
    hythm
    0.45
    Activations Density 0.513%

    No Known Activations