Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9682
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mer" and its variants or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.80
    abestanden
    -0.63
    complexType
    -0.61
    IonicModule
    -0.60
    TemporalType
    -0.58
     SEDS
    -0.57
    ValueStyle
    -0.54
    IUrlHelper
    -0.54
    asteroide
    -0.54
    InputTagHelper
    -0.53
    POSITIVE LOGITS
     MER
    0.96
     mer
    0.86
     Mer
    0.83
    Mer
    0.80
    MER
    0.74
     Mercu
    0.73
     Merk
    0.67
     Merr
    0.66
    mer
    0.64
     MERC
    0.64
    Activations Density 0.092%

    No Known Activations