© 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. 1-GEMMASCOPE-RES-16K
    11. 6484
    Prev
    Next
    INDEX
    Explanations

    elements related to database tables and their definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.87
     myſelf
    -0.84
    ⓧ
    -0.81
     themſelves
    -0.80
    NegativeButton
    -0.79
     itſelf
    -0.78
     дописавши
    -0.77
     vPvB
    -0.76
    PositiveButton
    -0.75
    UnusedPrivate
    -0.75
    POSITIVE LOGITS
    Table
    1.39
     table
    1.25
     Table
    1.22
    table
    1.19
    Tables
    1.16
    TABLE
    1.13
     tables
    1.08
    tables
    1.07
     TABLE
    1.03
     Tables
    0.97
    Activations Density 0.207%

    No Known Activations