© 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. 24-GEMMASCOPE-RES-16K
    11. 1805
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "re" indicating a repeated action or occurrence

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

    starting with "re"

    np_acts-logits-general · gemini-2.0-flash

    words starting with re

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.82
    addCriterion
    -0.79
    TagHelper
    -0.71
    UnitTesting
    -0.70
    PerformLayout
    -0.67
    ConstraintMaker
    -0.67
     BrowserModule
    -0.66
     ControllerBase
    -0.64
    intios
    -0.64
    BeginContext
    -0.64
    POSITIVE LOGITS
     للاسماء
    0.41
     surla
    0.39
    微
    0.38
     majority
    0.38
    LogError
    0.37
    eking
    0.37
    train
    0.37
    pertory
    0.37
    omial
    0.37
    ostringstream
    0.36
    Activations Density 0.171%

    No Known Activations