© 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. 9-GEMMASCOPE-RES-16K
    11. 9892
    Prev
    Next
    INDEX
    Explanations

    references to hardware and its components

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

    references to computer hardware components and technical specifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.46
    Boas
    -0.42
     enseña
    -0.37
    gameserver
    -0.37
     Lokales
    -0.37
     chofe
    -0.36
    VisualStudio
    -0.36
    Insight
    -0.36
    webElementXpaths
    -0.36
    المناصب
    -0.35
    POSITIVE LOGITS
     hardware
    1.85
     Hardware
    1.74
    Hardware
    1.71
    hardware
    1.70
    硬件
    1.39
    HARDWARE
    1.35
    hw
    0.86
     sprzę
    0.84
     HW
    0.84
     matériel
    0.80
    Activations Density 0.292%

    No Known Activations