© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14985
    Prev
    Next
    INDEX
    Explanations

    elements related to database schema definitions and attributes

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

    "id" and related database terms

    np_acts-logits-general · gemini-2.0-flash

    database id fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Numerade
    -0.62
     ویکی‌پدی
    -0.52
    //
    -0.48
    aarrggbb
    -0.48
    stylers
    -0.46
     gyhoeddwyd
    -0.46
    RegressionTest
    -0.45
    әрмәләр
    -0.44
    хьтан
    -0.43
    этому
    -0.43
    POSITIVE LOGITS
    AutoField
    0.74
    GeneratedValue
    0.45
    ValueGeneration
    0.42
    CloseOperation
    0.40
    ValueGenerated
    0.38
    WebpackPlugin
    0.37
    AutoScaleMode
    0.35
    TableId
    0.33
    BaseEntity
    0.32
     Id
    0.32
    Activations Density 0.072%

    No Known Activations