© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 12623
    Prev
    Next
    INDEX
    Explanations

    references to online platforms and the internet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    createClass
    -0.46
    spesies
    -0.43
     '{@
    -0.42
    Espèce
    -0.42
     uğ
    -0.41
     darah
    -0.41
    tagHelperRunner
    -0.41
    umque
    -0.40
     irl
    -0.39
    interopRequire
    -0.39
    POSITIVE LOGITS
     internet
    2.13
     Internet
    2.11
    Internet
    1.91
    internet
    1.88
     INTERNET
    1.75
    INTERNET
    1.59
    インターネット
    1.44
    互联网
    1.44
    ترنت
    1.23
     internetu
    1.23
    Activations Density 0.204%

    No Known Activations