© 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. 2081
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or narratives

    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
     Efq
    -1.09
     itſelf
    -1.05
     ་་
    -1.00
     Majefty
    -0.96
     Jefus
    -0.95
    ſelf
    -0.95
     raiſ
    -0.90
     Houſe
    -0.90
     ―――――
    -0.90
    ſelves
    -0.89
    POSITIVE LOGITS
     two
    1.48
    two
    1.32
     Two
    1.24
    Two
    1.23
     TWO
    1.21
    TWO
    1.15
     deux
    1.13
     zwei
    1.09
     three
    1.00
     duas
    0.92
    Activations Density 0.476%

    No Known Activations