© 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. 18-GEMMASCOPE-RES-16K
    11. 2102
    Prev
    Next
    INDEX
    Explanations

    references to news updates and releases

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

    time periods (day, week, month)

    np_acts-logits-general · gemini-2.0-flash

    weekly news and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Metacritic
    -0.42
     boycot
    -0.42
     įsi
    -0.37
     henvisninger
    -0.37
     Dokumentation
    -0.37
    
    -0.36
     laiko
    -0.36
    ほど
    -0.36
     beau
    -0.36
     protesting
    -0.35
    POSITIVE LOGITS
     weekly
    1.40
    weekly
    1.22
     monthly
    1.18
     Weekly
    1.16
    Weekly
    1.08
    monthly
    1.06
     Monthly
    1.05
     WEEKLY
    1.01
     hebdomada
    1.00
     daily
    0.99
    Activations Density 0.204%

    No Known Activations