© 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. 14689
    Prev
    Next
    INDEX
    Explanations

    references to files and file systems in code

    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
    retudo
    -0.62
    }")
    
    -0.57
     hoş
    -0.52
     Goodman
    -0.51
     HRT
    -0.50
    Aholisi
    -0.50
     kawaida
    -0.50
     Madsen
    -0.49
    '),
    
    -0.48
    onavir
    -0.48
    POSITIVE LOGITS
     file
    1.70
    File
    1.59
     File
    1.58
    file
    1.52
     files
    1.51
     Files
    1.34
     FILE
    1.34
     getFile
    1.30
    FILE
    1.25
    files
    1.23
    Activations Density 0.148%

    No Known Activations