© 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. 4-GEMMASCOPE-RES-16K
    6. 15439
    Prev
    Next
    INDEX
    Explanations

    references to Roman and Catholic history and traditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    versaire
    -0.58
    Personensuche
    -0.56
    Vezi
    -0.52
    ikum
    -0.49
    leine
    -0.47
     Normdatei
    -0.45
    Spoljašnje
    -0.44
    ioneta
    -0.44
     المعرف
    -0.44
     painting
    -0.43
    POSITIVE LOGITS
     Roman
    1.31
    Roman
    1.23
     ROMAN
    1.12
     roman
    1.11
    roman
    0.94
     Romans
    0.92
     rom
    0.91
     romana
    0.90
     ROM
    0.88
     romans
    0.85
    Activations Density 1.320%

    No Known Activations