© 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. 20-GEMMASCOPE-RES-16K
    11. 11166
    Prev
    Next
    INDEX
    Explanations

    phrases related to database status and actions

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

    emptiness or lack of information

    np_acts-logits-general · gemini-2.0-flash

    clean or clear databases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.75
    Referanser
    -0.65
    WebServlet
    -0.62
    **********/
    -0.59
     NgModule
    -0.58
    Organisateur
    -0.56
     هيا
    -0.56
    Portale
    -0.55
     Viator
    -0.54
    LEncoder
    -0.54
    POSITIVE LOGITS
     clean
    2.01
     clear
    1.72
    clean
    1.70
    clear
    1.62
     Clean
    1.55
    Clean
    1.53
    Clear
    1.52
     CLEAN
    1.51
     Clear
    1.51
     cleared
    1.49
    Activations Density 0.572%

    No Known Activations