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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 13943
    Prev
    Next
    INDEX
    Explanations

    instances of the word "when" in various contexts

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

    "When" followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    when, then what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.68
     serem
    -0.59
     gärna
    -0.58
     saiba
    -0.57
    them
    -0.56
    PreAuthorize
    -0.55
     réglable
    -0.55
     serata
    -0.53
     sebagai
    -0.51
     perché
    -0.50
    POSITIVE LOGITS
     asked
    1.25
     they
    1.14
     faced
    1.12
     confronted
    1.10
     we
    1.09
     compared
    1.01
     questioned
    0.92
     you
    0.92
     viewed
    0.88
     discussing
    0.87
    Activations Density 0.105%

    No Known Activations