© 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. 36-GEMMASCOPE-RES-16K
    6. 11746
    Prev
    Next
    INDEX
    Explanations

    questions seeking clarification or information, especially starting with 'why', 'how', and 'where'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.66
     propOrder
    -0.63
     estekak
    -0.62
     cuál
    -0.59
     Wiktionnaire
    -0.59
    存于互联网档案馆
    -0.58
    cuál
    -0.56
    Cuál
    -0.55
    出版年
    -0.54
     jaki
    -0.53
    POSITIVE LOGITS
     does
    1.13
     did
    1.00
    does
    0.71
     Does
    0.63
    Does
    0.61
    did
    0.58
     Did
    0.51
     DOES
    0.50
    DOES
    0.49
    Did
    0.47
    Activations Density 0.263%

    No Known Activations