© 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. 2-GEMMASCOPE-RES-16K
    6. 9339
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reserve" or related terms referencing a provision or allocation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setAction
    -0.38
    modelBuilder
    -0.37
    サイ
    -0.36
    drawSprites
    -0.36
    Meyer
    -0.35
     太郎
    -0.35
    dataIndex
    -0.35
    ยุ
    -0.35
     ansik
    -0.35
    WindowConstants
    -0.34
    POSITIVE LOGITS
     reserve
    1.57
     reserved
    1.45
     Reserve
    1.41
     RESERVE
    1.40
    reserve
    1.39
    Reserve
    1.36
     rental
    1.34
     reserving
    1.33
     reservation
    1.30
    reserved
    1.30
    Activations Density 0.138%

    No Known Activations