© 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. 3-GEMMASCOPE-RES-16K
    6. 8860
    Prev
    Next
    INDEX
    Explanations

    instances of the sequence "Mar" followed by specific tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pidou
    -0.82
    BibitemShut
    -0.71
    kegaard
    -0.69
     Sigism
    -0.63
     Brems
    -0.63
     препратки
    -0.63
     Asturias
    -0.60
    bibinfo
    -0.60
     enco
    -0.59
     Vek
    -0.59
    POSITIVE LOGITS
     Mar
    3.54
    Mar
    3.32
     mar
    3.22
     MAR
    2.97
    mar
    2.89
    MAR
    2.63
     Maru
    1.87
    Marg
    1.84
     Marr
    1.82
     Мар
    1.81
    Activations Density 0.075%

    No Known Activations