© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3999
    Prev
    Next
    INDEX
    Explanations

    terms related to classification and categorization of data or entities

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

    classification or categorization

    np_acts-logits-general · gemini-2.0-flash

    dividing and classifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    enterOuterAlt
    -0.58
    bootstrapcdn
    -0.55
    متن
    -0.51
     totalPrice
    -0.51
     PeEnEo
    -0.51
    UnknownFieldSet
    -0.50
    canActivate
    -0.48
    Addo
    -0.48
    DeleteBehavior
    -0.48
    replicas
    -0.48
    POSITIVE LOGITS
     classification
    2.03
     categor
    2.01
     categorization
    1.96
     categorize
    1.87
     classifications
    1.81
     classifying
    1.80
     classify
    1.73
     categories
    1.71
     Classification
    1.67
    classification
    1.62
    Activations Density 0.920%

    No Known Activations