© 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. 38-GEMMASCOPE-RES-16K
    6. 15649
    Prev
    Next
    INDEX
    Explanations

    instructions or recommendations related to travel preparations

    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
    doPost
    -0.41
    الحياه
    -0.39
     cucchiaio
    -0.36
    InSection
    -0.35
    defineProperty
    -0.35
    fromnode
    -0.35
    postDelayed
    -0.35
     aika
    -0.34
    UOUS
    -0.34
     malheure
    -0.34
    POSITIVE LOGITS
     sunscreen
    0.99
     snacks
    0.92
     Sunscreen
    0.87
     Snacks
    0.81
    Snacks
    0.79
     toiletries
    0.75
     bottled
    0.75
     packed
    0.73
     flasks
    0.72
     umbrellas
    0.71
    Activations Density 0.241%

    No Known Activations