Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10004
    Prev
    Next
    INDEX
    Explanations

    words related to time travel.

    oai_token-act-pair · gemini-1.5-proTriggered by @alecksfmail

    concepts related to time travel and movement across dimensions or timelines.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @hanshan1988

    words related to time travel and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.71
    ArgsConstructor
    -0.70
    BeginContext
    -0.70
     propOrder
    -0.68
    UnusedPrivate
    -0.66
    NameInMap
    -0.61
    setVerticalGroup
    -0.59
    invokeLater
    -0.59
    sizeCache
    -0.59
    rawDesc
    -0.58
    POSITIVE LOGITS
     dimension
    1.08
     dimensional
    0.98
     space
    0.92
     dimensions
    0.92
     Dimension
    0.92
    dimension
    0.91
    dimensional
    0.90
     portal
    0.89
     tele
    0.89
     Time
    0.87
    Activations Density 0.350%

    No Known Activations