© 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. 15746
    Prev
    Next
    INDEX
    Explanations

    comparative phrases involving the word "over" and expressions indicating preference or superiority

    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
    حياته
    -0.69
     mergeFrom
    -0.61
    cista
    -0.55
     $_"
    -0.52
    $.}
    -0.52
    ).}
    -0.51
    脚注
    -0.50
     zufolge
    -0.50
    @[+][
    -0.48
    onos
    -0.48
    POSITIVE LOGITS
     than
    1.04
     THAN
    1.02
     Than
    0.97
    Than
    0.96
    than
    0.89
     versus
    0.88
     vs
    0.83
    жели
    0.77
    THAN
    0.76
     niż
    0.76
    Activations Density 0.426%

    No Known Activations