© 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. 18-GEMMASCOPE-RES-16K
    11. 8221
    Prev
    Next
    INDEX
    Explanations

    instances of the word "further" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Further"

    np_acts-logits-general · gemini-2.0-flash

    further elaboration or addendum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grama
    -0.51
     setempat
    -0.50
    bootstrapcdn
    -0.50
     Doran
    -0.49
    monių
    -0.49
     préfé
    -0.49
    ActionEvent
    -0.49
     igenom
    -0.49
    arraycopy
    -0.49
    لول
    -0.48
    POSITIVE LOGITS
     afield
    0.96
     propOrder
    0.70
    AsUp
    0.69
    verwijspagina
    0.69
     ado
    0.67
     deepen
    0.67
     Paglinawan
    0.66
    rungsseite
    0.65
    存于互联网档案馆
    0.64
    InSection
    0.63
    Activations Density 0.190%

    No Known Activations