© 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. 34-GEMMASCOPE-RES-16K
    11. 11753
    Prev
    Next
    INDEX
    Explanations

    sentences related to technical processes, warnings, and conditions in server and programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.42
    __(/*!
    -0.42
    Developed
    -0.40
     bär
    -0.39
     &___
    -0.38
    Driven
    -0.35
    ARROLLO
    -0.35
    StructEnd
    -0.35
    developed
    -0.35
    Selective
    -0.35
    POSITIVE LOGITS
     automatically
    0.89
     defaulted
    0.68
     behave
    0.64
     자동
    0.63
     automatisch
    0.62
    自动
    0.62
     автоматически
    0.62
     Automatically
    0.62
     reverted
    0.61
     automatiquement
    0.61
    Activations Density 0.809%

    No Known Activations