© 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 EvalsExportsinterp-engineNEWAPI 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. 8558
    Prev
    Next
    INDEX
    Explanations

    terms related to online processes and digital transactions

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

    the internet or digital media

    np_acts-logits-general · gemini-2.0-flash

    online and internet

    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
    úgó
    -0.39
    таратура
    -0.31
     fuo
    -0.27
    exitRule
    -0.27
     Autorisations
    -0.25
    帖最后由
    -0.24
    ěž
    -0.24
    createClass
    -0.22
     scoring
    -0.22
    InputTagHelper
    -0.21
    POSITIVE LOGITS
     online
    2.44
    online
    1.96
     Online
    1.93
     ONLINE
    1.91
     internet
    1.88
    Online
    1.88
     Internet
    1.81
     digital
    1.77
     онлайн
    1.74
    Internet
    1.73
    Activations Density 0.561%

    No Known Activations