© 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. 30-GEMMASCOPE-RES-16K
    11. 12735
    Prev
    Next
    INDEX
    Explanations

    names related to East Asian culture, particularly focusing on individuals and places associated with "Shang" and "Liang"

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

    Contains "ang" or "Sag"

    np_acts-logits-general · gemini-2.0-flash

    Liang Sag Trail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.60
    Identyfik
    -0.55
     noDo
    -0.55
     ویکی‌پدی
    -0.54
    存于互联网档案馆
    -0.54
     disambiguazione
    -0.52
    setVerticalGroup
    -0.49
    parsedMessage
    -0.47
    delwed
    -0.47
    Hentet
    -0.47
    POSITIVE LOGITS
    dang
    0.48
    ANG
    0.46
    ang
    0.44
    PickerController
    0.44
    tang
    0.44
    PasswordEncoder
    0.43
    rang
    0.43
    gggg
    0.43
     Dang
    0.42
     Blom
    0.41
    Activations Density 0.139%

    No Known Activations