© 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. 31-GEMMASCOPE-RES-16K
    11. 15645
    Prev
    Next
    INDEX
    Explanations

    references to specific classifications or categories, often marked by letters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    single capital letters that appear at the beginning of proper nouns or abbreviations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    บรร
    -0.40
     työn
    -0.39
     ins
    -0.36
     näytte
    -0.35
     övers
    -0.35
    føl
    -0.35
     tacón
    -0.35
     împre
    -0.35
    店頭
    -0.35
     Nagel
    -0.35
    POSITIVE LOGITS
     SwiftUI
    0.61
    MLLoader
    0.60
     Audiodateien
    0.60
     Enix
    0.57
    $_['
    0.57
    PDO
    0.54
    UVWXYZ
    0.54
    WP
    0.54
     Савезне
    0.54
    INSEE
    0.54
    Activations Density 0.883%

    No Known Activations