© 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. 13298
    Prev
    Next
    INDEX
    Explanations

    sequences and relationships in structured data representations, particularly in algorithms or mathematical contexts

    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
    bentukan
    -0.42
     &___
    -0.40
    ずみ
    -0.36
    tagHelperRunner
    -0.36
    uxley
    -0.35
    ỡng
    -0.35
     vacun
    -0.34
     насељу
    -0.34
    qvarna
    -0.34
    bsch
    -0.34
    POSITIVE LOGITS
     reverse
    3.48
     reversed
    3.28
     Reverse
    3.08
    reverse
    2.91
     reverses
    2.89
    Reverse
    2.88
     reversing
    2.84
     inverse
    2.78
     reversal
    2.77
     revers
    2.59
    Activations Density 2.040%

    No Known Activations