© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3642
    Prev
    Next
    INDEX
    Explanations

    the word "When."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::_('
    -0.66
    deleteById
    -0.66
     vĩnh
    -0.65
     lenne
    -0.59
    raszam
    -0.56
    expandindo
    -0.55
     continuant
    -0.54
     razie
    -0.54
     σήμερα
    -0.54
     surla
    -0.53
    POSITIVE LOGITS
    When
    1.46
     When
    1.44
    Когда
    1.05
    Whenever
    1.03
     Когда
    1.02
     Wanneer
    1.00
     Lorsque
    0.99
     Cuando
    0.99
     Whenever
    0.98
     Quando
    0.97
    Activations Density 0.075%

    No Known Activations