© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 818
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the use or presence of the word "on"

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

    "on" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    ungszeit
    -0.40
    CppMethod
    -0.38
    তথ্যসূত্র
    -0.36
     czer
    -0.36
    ///</
    -0.35
     sfeer
    -0.34
    く
    -0.33
     geest
    -0.33
    nictví
    -0.32
     ruimte
    -0.32
    POSITIVE LOGITS
     behalf
    0.85
     ועל
    0.82
    isOn
    0.79
     on
    0.77
     روی
    0.74
     onData
    0.74
     وعلى
    0.73
     occasion
    0.69
     onView
    0.68
    บน
    0.68
    Activations Density 0.457%

    No Known Activations