© 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. 2251
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to inevitability and tension in a storyline

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

    Expressing inevitability or something happening "later"

    np_acts-logits-general · gemini-2.0-flash

    eventual outcomes and timing

    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
     ogóle
    -0.66
    стья
    -0.52
    aguars
    -0.52
    paramref
    -0.51
    <bos>
    -0.48
     arşivlendi
    -0.48
    allage
    -0.47
     understandings
    -0.45
    confused
    -0.45
    lepiej
    -0.45
    POSITIVE LOGITS
     inevitable
    1.26
     sooner
    1.20
    inev
    1.14
     inevit
    1.14
     inevitably
    1.07
     eventually
    1.05
     Eventually
    1.04
    Eventually
    1.04
    いつか
    1.02
     irgendwann
    1.00
    Activations Density 0.294%

    No Known Activations