© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4776
    Prev
    Next
    INDEX
    Explanations

    keywords related to political events and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fg
    -0.47
    truc
    -0.45
     Wör
    -0.44
    Hers
    -0.43
    สบ
    -0.42
     Pendleton
    -0.42
    %
    -0.42
    هب
    -0.41
    mmä
    -0.41
    läs
    -0.40
    POSITIVE LOGITS
    Bangladesh
    0.96
     Bangladesh
    0.95
    ladesh
    0.90
     Dhaka
    0.89
     ویکی‌پدیا
    0.88
    AndEndTag
    0.85
     Banglades
    0.83
    Datuak
    0.82
    
    0.82
    Hochspringen
    0.80
    Activations Density 0.068%

    No Known Activations