© 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. 9209
    Prev
    Next
    INDEX
    Explanations

    references to "deep" in various contexts, particularly regarding deep-fried food or the Deep State

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

    "deep"

    np_acts-logits-general · gemini-2.0-flash

    deep State

    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
    +#+#
    -0.65
     disambiguazione
    -0.57
     autorytatywna
    -0.54
    帖最后由
    -0.53
     ExecuteAsync
    -0.53
    出版年
    -0.53
    oredCriteria
    -0.52
    RegressionTest
    -0.51
    Демографія
    -0.51
    Derbyniad
    -0.47
    POSITIVE LOGITS
     deep
    1.07
     Deep
    1.05
    deep
    1.04
     DEEP
    1.02
    Deep
    1.01
    DEEP
    0.96
    depth
    0.85
     depth
    0.82
     deepen
    0.82
     deeply
    0.79
    Activations Density 0.093%

    No Known Activations