© 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. 3411
    Prev
    Next
    INDEX
    Explanations

    terms related to political leadership and roles within organizations

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

    following titles, like "Chair", or "Spokes"

    np_acts-logits-general · gemini-2.0-flash

    chair, spokesperson, congress, council

    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
    المكان
    -0.58
     snippetHide
    -0.55
     BoxFit
    -0.55
    matchCondition
    -0.53
    AndEndTag
    -0.51
    IntoConstraints
    -0.51
    Bronnen
    -0.49
     saites
    -0.49
     ivelany
    -0.48
    agisse
    -0.48
    POSITIVE LOGITS
    men
    2.15
    man
    2.08
    woman
    2.00
    person
    1.80
    MAN
    1.73
    persons
    1.69
     man
    1.66
    MEN
    1.65
    mans
    1.63
    women
    1.52
    Activations Density 0.301%

    No Known Activations