© 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 EvalsExportsinterp-engineNEWAPI 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. 1271
    Prev
    Next
    INDEX
    Explanations

    characters and roles associated with authority and social dynamics

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

    that describe a person

    np_acts-logits-general · gemini-2.0-flash

    people who are professionals or in roles

    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
     Their
    -0.80
    Their
    -0.79
     their
    -0.74
    their
    -0.73
    themselves
    -0.65
     THEIR
    -0.65
     themselves
    -0.65
     deres
    -0.64
     loro
    -0.57
     Италијани
    -0.55
    POSITIVE LOGITS
     who
    1.47
     whom
    1.14
    who
    1.00
    whom
    0.93
     himself
    0.92
     bernama
    0.87
     whofe
    0.86
     namens
    0.84
     quien
    0.84
     whose
    0.83
    Activations Density 0.495%

    No Known Activations