© 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. 2709
    Prev
    Next
    INDEX
    Explanations

    discussions around ideological conflicts and battles, especially those involving governance and social systems

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

    Conflict, fights, or rivalries

    np_acts-logits-general · gemini-2.0-flash

    conflict and rivalry

    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
     BrowserModule
    -0.57
    GOTREF
    -0.55
     ویکی‌پدیای
    -0.53
     Picchu
    -0.52
    gatsby
    -0.52
    Према
    -0.52
    WriteLiteral
    -0.51
    Obras
    -0.50
     فريبيس
    -0.50
    espół
    -0.50
    POSITIVE LOGITS
     battle
    1.43
     battles
    1.37
     rivalry
    1.30
     fought
    1.30
     fight
    1.26
     pitting
    1.22
    battle
    1.22
     battled
    1.21
     fights
    1.18
     showdown
    1.14
    Activations Density 0.439%

    No Known Activations