© 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. 30-GEMMASCOPE-RES-16K
    11. 10600
    Prev
    Next
    INDEX
    Explanations

    references to digital content and online experiences

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

    meaning "after all" in other languages

    np_acts-logits-general · gemini-2.0-flash

    after all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.59
    addCriterion
    -0.48
    itinéraire
    -0.48
    HandlerContext
    -0.45
    addPreferredGap
    -0.44
     noDo
    -0.44
    contentLoaded
    -0.43
     AssemblyCompany
    -0.42
    igshid
    -0.42
    awtextra
    -0.41
    POSITIVE LOGITS
    毕竟
    1.73
    畢竟
    1.70
     Schließlich
    1.56
     ведь
    1.40
     Ведь
    1.37
    Ведь
    1.36
     przecież
    1.23
     schließlich
    1.14
     bowiem
    1.13
     infatti
    0.98
    Activations Density 0.275%

    No Known Activations