© 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. 3-GEMMASCOPE-RES-16K
    11. 7888
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "that" as well as related pronouns like "who" and "whose."

    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
     урна
    -0.57
    rinology
    -0.51
    ,"\
    -0.50
    HasBeenSet
    -0.49
    دانشنامهٔ
    -0.48
     us
    -0.47
    痺
    -0.47
     eventualmente
    -0.47
    itively
    -0.46
    Einzelnachweise
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.83
     MonoBehaviour
    0.74
    AnchorStyles
    0.67
    VideoCapture
    0.67
    AddTagHelper
    0.66
    ChildScrollView
    0.66
     '\\;'
    0.64
    Portale
    0.64
    npos
    0.62
     bParam
    0.59
    Activations Density 0.253%

    No Known Activations