© 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. 4-GEMMASCOPE-RES-16K
    11. 9612
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Euph
    -0.78
     Jef
    -0.77
     duels
    -0.72
    Tikang
    -0.72
     Marcell
    -0.71
     Hic
    -0.70
    unhofer
    -0.69
     Nib
    -0.68
     Noc
    -0.67
     Viol
    -0.67
    POSITIVE LOGITS
     organization
    2.25
     organizations
    2.14
     Organization
    2.05
     organisation
    2.01
     Organizations
    1.97
    Organizations
    1.91
     organisations
    1.91
     Organisation
    1.84
    organizations
    1.81
    organization
    1.73
    Activations Density 0.051%

    No Known Activations