© 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. 15-GEMMASCOPE-RES-16K
    6. 1403
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and structures involving underlined variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Melon
    -0.54
     sản
    -0.54
    Moss
    -0.52
    newVal
    -0.50
     Pebble
    -0.49
    mtd
    -0.48
    Melon
    -0.47
    coll
    -0.47
     Milla
    -0.47
     Peppers
    -0.47
    POSITIVE LOGITS
    <u>
    1.19
    underline
    0.97
    </u>
    0.62
     utafitiHapana
    0.53
     Segura
    0.51
    ExecuteReader
    0.50
    Underline
    0.50
    XmlAccessType
    0.50
    /*---
    0.49
     Humphreys
    0.47
    Activations Density 0.105%

    No Known Activations