© 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. 38-GEMMASCOPE-RES-16K
    11. 15168
    Prev
    Next
    INDEX
    Explanations

    elements related to formal communication and the presentation of findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.73
    __*/
    -0.66
     оригіналу
    -0.54
    exitRule
    -0.51
    endphp
    -0.50
    ArgumentParser
    -0.50
    tonode
    -0.48
    rawDesc
    -0.47
    躇
    -0.45
    hasMoreElements
    -0.45
    POSITIVE LOGITS
     that
    3.31
    that
    1.72
     That
    1.62
    That
    1.59
     bahwa
    1.58
     THAT
    1.52
     rằng
    1.39
     bahawa
    1.37
     że
    1.32
     thats
    1.30
    Activations Density 8.915%

    No Known Activations