© 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. 16-GEMMASCOPE-RES-16K
    11. 2213
    Prev
    Next
    INDEX
    Explanations

    references to individuals and groups, particularly in relation to societal roles and actions

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

    "People" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    people and their states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.56
    ↵↵
    -0.52
    …
    -0.49
     pro
    -0.47
     The
    -0.45
    ↵
    -0.45
    ...
    -0.44
     Pro
    -0.43
     the
    -0.43
     :
    -0.42
    POSITIVE LOGITS
     nahilalakip
    1.10
     myſelf
    0.99
    SourceChecksum
    0.99
     iſt
    0.92
     houſe
    0.92
     itſelf
    0.91
     ſtate
    0.90
     uſed
    0.90
     ModelExpression
    0.88
     beſt
    0.88
    Activations Density 0.358%

    No Known Activations