Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 11750
    Prev
    Next
    INDEX
    Explanations

    references to groups of people or communities, particularly in a socio-political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inalis
    -0.49
     supone
    -0.49
    SearchTree
    -0.48
     Reglamento
    -0.47
    χει
    -0.46
    utex
    -0.45
    govine
    -0.45
    XtraGrid
    -0.45
     Dominicana
    -0.44
    naeus
    -0.44
    POSITIVE LOGITS
     peoples
    0.99
    oples
    0.94
    people
    0.91
     PEOPLE
    0.90
     Peoples
    0.88
    PEOPLE
    0.85
    новништво
    0.85
     peuple
    0.82
     popolo
    0.80
     people
    0.80
    Activations Density 0.213%

    No Known Activations