© 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. 16-GEMMASCOPE-RES-16K
    11. 7166
    Prev
    Next
    INDEX
    Explanations

    instances of potential or conditional language

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

    Follows "Q" or a period

    np_acts-logits-general · gemini-2.0-flash

    nevertheless, nonetheless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.68
     estimés
    -0.67
     but
    -0.60
    enumi
    -0.53
    GraphicsUnit
    -0.52
    tagHelperRunner
    -0.52
    のですが
    -0.51
    Aktualisiert
    -0.48
     αλλά
    -0.48
    もありますが
    -0.47
    POSITIVE LOGITS
     nonetheless
    1.52
     nevertheless
    1.36
     ändå
    1.08
    etheless
    1.07
     néanmoins
    0.95
     dennoch
    0.94
    Nonetheless
    0.92
     trotzdem
    0.87
     immerhin
    0.83
    それでも
    0.82
    Activations Density 0.412%

    No Known Activations