© 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. 12-GEMMASCOPE-RES-16K
    6. 6769
    Prev
    Next
    INDEX
    Explanations

    phrases or terms that indicate definitions, names, or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     قاب
    -0.36
     mahd
    -0.32
     budget
    -0.32
     énergé
    -0.30
     morales
    -0.30
     tavo
    -0.30
     lä
    -0.29
     DPRD
    -0.29
    yty
    -0.28
     tamen
    -0.28
    POSITIVE LOGITS
     called
    0.84
    called
    0.77
     Called
    0.77
    parsedMessage
    0.73
     termed
    0.73
     noemen
    0.73
     disebut
    0.73
     chamado
    0.72
    被称为
    0.72
     sogenannten
    0.71
    Activations Density 0.594%

    No Known Activations