© 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. 20-GEMMASCOPE-RES-16K
    6. 6392
    Prev
    Next
    INDEX
    Explanations

    phrases related to significance and continuity in narratives

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

    technical language about systems and processes.

    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
     huiles
    -0.37
    håll
    -0.36
     évêque
    -0.35
     rêve
    -0.33
     verres
    -0.32
     bénévol
    -0.32
     mépris
    -0.30
     vendas
    -0.30
     meubles
    -0.30
     recours
    -0.30
    POSITIVE LOGITS
    LookAnd
    1.27
    :✨
    0.72
    setupUi
    0.68
    RenderAtEndOf
    0.68
    RTGC
    0.65
    onViewCreated
    0.64
     CURIAM
    0.59
     ostavi
    0.59
    ValueStyle
    0.57
    şört
    0.57
    Activations Density 0.734%

    No Known Activations