© 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. 20-GEMMASCOPE-RES-16K
    11. 2765
    Prev
    Next
    INDEX
    Explanations

    structured data related to programming and data manipulation

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

    programming or code-related syntax and structures, particularly involving variables, loops, and technical documentation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.85
    tagHelperRunner
    -0.82
     pinulongan
    -0.68
    новништво
    -0.66
    IVEREF
    -0.65
    Chham
    -0.65
     otomatig
    -0.63
     Wicidata
    -0.62
    səhifə
    -0.61
     Meksiku
    -0.61
    POSITIVE LOGITS
    seamnă
    0.37
    　
    0.32
    —
    0.29
    ēd
    0.28
    Ah
    0.28
     чет
    0.27
    –
    0.27
    <strong>
    0.27
     пос
    0.26
     
    0.26
    Activations Density 0.430%

    No Known Activations