© 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. 18-GEMMASCOPE-RES-16K
    11. 9861
    Prev
    Next
    INDEX
    Explanations

    content related to company operations and organizational structure

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

    Company locations and headquarters

    np_acts-logits-general · gemini-2.0-flash

    company headquarters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.66
    
    -0.64
     Roskov
    -0.48
    Hentet
    -0.45
    ftagPool
    -0.45
    simpleType
    -0.44
     trilha
    -0.42
     propOrder
    -0.41
    ัติ
    -0.40
     tramonto
    -0.40
    POSITIVE LOGITS
     headquarters
    2.17
     Headquarters
    1.82
     offices
    1.76
     HQ
    1.68
    Headquarters
    1.66
     office
    1.59
     headquartered
    1.59
     sede
    1.45
     Offices
    1.38
     siège
    1.35
    Activations Density 0.332%

    No Known Activations