© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7890
    Prev
    Next
    INDEX
    Explanations

    phrases related to time travel and historical events

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

    "future" and time travel

    np_acts-logits-general · gemini-2.0-flash

    future and past actions

    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
    duma
    -0.68
    .(*
    -0.65
    Insets
    -0.63
    BeginContext
    -0.63
    createServer
    -0.62
    TagMode
    -0.61
     Langmuir
    -0.58
    djangoproject
    -0.58
    ießen
    -0.56
    cenary
    -0.56
    POSITIVE LOGITS
     future
    1.92
    future
    1.75
    Future
    1.73
     Future
    1.70
     FUTURE
    1.57
     futuro
    1.52
    FUTURE
    1.51
    未来
    1.30
     toekomst
    1.26
     futur
    1.25
    Activations Density 0.337%

    No Known Activations