© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12966
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and discussions related to liability and legal implications

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

    The neuron activates strongly for the word "Whether" at the beginning of conditional or alternative clauses, particularly when it introduces phrases presenting options or scenarios (e.g., "Whether you want," "Whether known by," "Whether it's").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    constructions that introduce alternatives or choices, especially the conditional framing that contrasts options with “or.”

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.55
    تقاوى
    -0.47
     jadx
    -0.39
    Hozzáférés
    -0.36
    autoreleasepool
    -0.34
    zarchiwizowane
    -0.34
     beginnetje
    -0.34
     ✭✭
    -0.33
     cof
    -0.33
    Παραπομπές
    -0.33
    POSITIVE LOGITS
    Whether
    0.66
     Whether
    0.64
     WHETHER
    0.60
     whether
    0.58
    whether
    0.57
    Regardless
    0.54
    不论
    0.52
     سواء
    0.52
     fisuras
    0.51
    Whatever
    0.50
    Activations Density 0.289%

    No Known Activations