© 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. 5571
    Prev
    Next
    INDEX
    Explanations

    references to digital media and their distribution

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

    discussions about Amazon's business strategy and technology products, particularly tablets and Kindle devices.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    discussions analyzing Amazon’s Kindle device strategy—especially tablets—including hardware economics, monetization, and comparisons with competitors like Apple/Android.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    discussions about Amazon's business strategy and device ecosystem.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    LDR
    -0.48
     locaux
    -0.43
     esponja
    -0.41
     pratica
    -0.40
    ChildScrollView
    -0.40
    Parameteri
    -0.39
     Sms
    -0.38
    fortunately
    -0.38
     practised
    -0.38
     HR
    -0.38
    POSITIVE LOGITS
     propOrder
    0.59
     semiconductors
    0.55
    pidou
    0.52
    Sucesor
    0.51
     semiconductor
    0.49
     technological
    0.49
     revolutionaries
    0.48
    각주
    0.47
     iterations
    0.47
     devices
    0.46
    Activations Density 0.375%

    No Known Activations