© 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. 9-GEMMASCOPE-RES-16K
    6. 9828
    Prev
    Next
    INDEX
    Explanations

    geographical and location-related references, particularly in Switzerland and Wisconsin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SqlDbType
    -0.88
     Kohlen
    -0.79
     COAL
    -0.77
     coals
    -0.74
     redhead
    -0.74
     Coal
    -0.74
     Kuta
    -0.73
    dafx
    -0.73
     Siberian
    -0.72
     Khr
    -0.71
    POSITIVE LOGITS
     Wisconsin
    0.82
     Switzerland
    0.81
     Swiss
    0.80
    Wisconsin
    0.76
    Milwaukee
    0.75
     Milwaukee
    0.75
     Suisse
    0.74
     WISCONSIN
    0.73
    Switzerland
    0.72
    NgModule
    0.71
    Activations Density 0.824%

    No Known Activations