© 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-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 665
    Prev
    Next
    INDEX
    Explanations

    special symbols and mathematical notations often used in scientific contexts

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

    DR moment, Chernozhukov

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ویکی‌پدیا
    -0.49
     Josephus
    -0.35
    MENAFN
    -0.35
    pédie
    -0.34
    ötzlich
    -0.33
    ≧
    -0.32
    ciatore
    -0.32
     affichés
    -0.32
    cepter
    -0.32
    kendo
    -0.32
    POSITIVE LOGITS
    :✨
    0.67
    TypedDataSet
    0.56
     autorytatywna
    0.55
    izr
    0.51
     '\\;'
    0.50
    ---*/
    0.49
    %)$
    0.48
    Демографія
    0.47
     Roskov
    0.47
     चीज़ों
    0.46
    Activations Density 0.086%

    No Known Activations