© 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. 16-GEMMASCOPE-RES-16K
    11. 13656
    Prev
    Next
    INDEX
    Explanations

    keywords related to governance and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.64
    intios
    -0.61
    ⓘ
    -0.59
    IndentedString
    -0.56
    Cyfeiriadau
    -0.55
    WebElementEntity
    -0.54
    קישורים
    -0.53
    лтамалар
    -0.52
    хьтан
    -0.50
    COUVER
    -0.50
    POSITIVE LOGITS
     kicked
    0.39
     wildly
    0.38
     gewo
    0.37
     Dafür
    0.37
    แรง
    0.35
    ammans
    0.35
     stringBy
    0.35
     kicks
    0.33
     kicking
    0.33
    __((
    0.32
    Activations Density 0.776%

    No Known Activations