© 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. 1-GEMMASCOPE-RES-16K
    11. 15247
    Prev
    Next
    INDEX
    Explanations

    the word "originally" and its variations, indicating a focus on the historical or initial context of events or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Slat
    -0.53
    waitKey
    -0.51
     Mam
    -0.51
    Vz
    -0.50
    NewGuid
    -0.50
     rest
    -0.50
     sap
    -0.49
    var
    -0.49
     direction
    -0.48
    Зна
    -0.47
    POSITIVE LOGITS
     initially
    1.98
     originally
    1.86
     inicialmente
    1.82
     originalmente
    1.74
     normally
    1.73
     ordinarily
    1.63
    Initially
    1.63
     Initially
    1.60
    originally
    1.58
     traditionally
    1.56
    Activations Density 0.114%

    No Known Activations