© 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. 15846
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and expressions related to vectors and equations

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

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    will be / is / can

    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
    RetentionPolicy
    -0.70
    IUrlHelper
    -0.63
     Normdatei
    -0.60
     initComponents
    -0.59
    __((
    -0.58
    Personendaten
    -0.55
    abstractmethod
    -0.54
     Waray
    -0.54
     main
    -0.50
    Referències
    -0.50
    POSITIVE LOGITS
     comportements
    0.71
     quelcon
    0.69
     dobbiamo
    0.69
     appunto
    0.67
    わけです
    0.67
     circonstances
    0.66
     nécessairement
    0.65
     bucal
    0.63
     osserv
    0.63
     plainte
    0.62
    Activations Density 1.525%

    No Known Activations