© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 4129
    Prev
    Next
    INDEX
    Explanations

    names and titles relevant to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    -0.71
     f
    -0.70
     g
    -0.69
     D
    -0.69
     C
    -0.69
     G
    -0.69
     F
    -0.68
     re
    -0.67
     
    -0.67
     B
    -0.67
    POSITIVE LOGITS
     itſelf
    1.23
     Monfieur
    1.19
     Efq
    1.19
     Jefus
    1.17
     Majefty
    1.16
     Theſe
    1.15
     againſt
    1.14
     themſelves
    1.13
     ſeveral
    1.09
     Anſ
    1.09
    Activations Density 2.614%

    No Known Activations