© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8063
    Prev
    Next
    INDEX
    Explanations

    the word "hence" used as a transitional or causal connector in the text

    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
    ์ตูน
    -0.77
     Corea
    -0.71
    thing
    -0.68
     Basili
    -0.67
    ORPG
    -0.67
     tires
    -0.63
    ordnet
    -0.63
     LoginComponent
    -0.62
     (_.
    -0.62
    tes
    -0.61
    POSITIVE LOGITS
     hence
    2.14
    hence
    2.09
    Hence
    2.06
     Hence
    1.94
     therefore
    1.01
     виправивши
    0.99
     Daarom
    0.99
     поэтому
    0.99
    Поэтому
    0.97
     henceforth
    0.94
    Activations Density 0.063%

    No Known Activations