© 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. 7603
    Prev
    Next
    INDEX
    Explanations

    numerical values and their formatting within contexts related to data or statistics

    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
     الحره
    -0.47
    bootstrapcdn
    -0.43
    hyrchwyd
    -0.43
    ckså
    -0.35
    wapV
    -0.34
     materia
    -0.34
    Twenty
    -0.33
     Twenty
    -0.31
    SizeMode
    -0.30
    osť
    -0.29
    POSITIVE LOGITS
    
    0.62
    期刊论文
    0.61
     ninth
    0.60
     tenth
    0.59
    ыгана
    0.58
     Ninth
    0.56
    ьаж
    0.56
     nine
    0.54
     intptr
    0.53
     Tenth
    0.52
    Activations Density 0.882%

    No Known Activations