© 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. 6-GEMMASCOPE-RES-16K
    6. 12870
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "when" to identify instances of events or conditions being described

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.73
    ::_('
    -0.71
    KommentareTeilen
    -0.71
     Danke
    -0.68
    iestety
    -0.67
    adaptiveStyles
    -0.67
     Suggest
    -0.67
     ביותר
    -0.65
     NUKAT
    -0.64
    Dziękuję
    -0.64
    POSITIVE LOGITS
    When
    1.54
     When
    1.52
    WHEN
    1.22
    when
    1.19
     when
    1.14
     WHEN
    1.13
    Cuando
    1.08
     Quando
    1.07
    Quando
    1.06
     Cuando
    1.06
    Activations Density 0.073%

    No Known Activations