© 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. 20-GEMMASCOPE-RES-16K
    11. 8826
    Prev
    Next
    INDEX
    Explanations

    names of important political figures and events related to governance

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

    Tokens before or related to a name/title/pronoun

    np_acts-logits-general · gemini-2.0-flash

    personally appointed or ordered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.61
    sbericht
    -0.59
    Carriera
    -0.56
    Abp
    -0.52
     ModelExpression
    -0.50
    
    -0.50
    CppCodeGen
    -0.50
     métiers
    -0.50
     convertView
    -0.50
     milik
    -0.49
    POSITIVE LOGITS
     personally
    1.45
     persönlich
    1.16
     personalmente
    1.11
     Personally
    1.02
     personal
    0.95
     лично
    0.93
    亲自
    0.90
    Personal
    0.86
    Personally
    0.86
    PERSONAL
    0.85
    Activations Density 0.405%

    No Known Activations