© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 25-GEMMASCOPE-RES-16K
    11. 14446
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms or references to criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gdx
    -0.66
     Oman
    -0.66
    
    -0.65
    rungsseite
    -0.61
     Haf
    -0.61
    Oman
    -0.60
     Sarawak
    -0.59
     Norway
    -0.59
     Newfoundland
    -0.58
     Lesotho
    -0.57
    POSITIVE LOGITS
     Chicago
    2.51
     Illinois
    2.34
    Chicago
    2.25
    Illinois
    2.09
     CHICAGO
    2.04
     chicago
    2.00
    chicago
    1.92
     ILLINOIS
    1.89
    CHICAGO
    1.81
     IL
    1.58
    Activations Density 0.546%

    No Known Activations