© 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. 11056
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "theme" and related concepts in context

    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
    Diweddarwch
    -0.75
     rhestr
    -0.72
     concentrating
    -0.67
    ⮕
    -0.65
    ⓧ
    -0.62
     للاسماء
    -0.60
     avoit
    -0.60
     Cortex
    -0.59
    دانشنامهٔ
    -0.58
     transférez
    -0.58
    POSITIVE LOGITS
     theme
    3.07
    theme
    2.59
     themes
    2.59
     Theme
    2.54
    Theme
    2.25
     THEME
    2.20
     Themes
    2.18
    themes
    2.00
    THEME
    1.94
     thème
    1.91
    Activations Density 0.064%

    No Known Activations