© 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. 7732
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "M" or references to authors with initials involving "M"

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

    Initials

    np_acts-logits-general · gemini-2.0-flash

    M followed by abbreviations and names

    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
    WebVitals
    -0.72
    ImageContext
    -0.66
    ttino
    -0.54
    featureID
    -0.52
    ganu
    -0.51
    XMLSchema
    -0.50
    __":
    -0.50
     esternos
    -0.48
    pexpr
    -0.48
    createServer
    -0.48
    POSITIVE LOGITS
    MemoryWarning
    0.62
    ViewImports
    0.60
     GIPHY
    0.54
    MessageTagHelper
    0.52
    artin
    0.52
     intensification
    0.49
    ifs
    0.49
    cln
    0.49
    NamedQueries
    0.49
    urgia
    0.48
    Activations Density 0.238%

    No Known Activations