© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13718
    Prev
    Next
    INDEX
    Explanations

    references to the term "div" and its variations in different contexts

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

    "Div" and variations

    np_acts-logits-general · gemini-2.0-flash

    div followed by 'is', 'i', 'orce', 'X', 'shot', 'iding'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.81
    encodeWith
    -0.78
     EconPapers
    -0.75
    StoreMessageInfo
    -0.71
     MenuView
    -0.71
     Agamemnon
    -0.70
     puntual
    -0.68
     transfieras
    -0.68
    lccn
    -0.67
    Бележки
    -0.67
    POSITIVE LOGITS
     Div
    0.70
     DIV
    0.69
    Div
    0.65
     div
    0.63
     divisor
    0.59
    div
    0.57
     divisions
    0.57
     divis
    0.57
    iding
    0.56
     divi
    0.55
    Activations Density 0.105%

    No Known Activations