© 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. 18-GEMMASCOPE-RES-16K
    11. 15879
    Prev
    Next
    INDEX
    Explanations

    discussions of choices and allegiances in conflict situations

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

    Choosing a side or taking sides

    np_acts-logits-general · gemini-2.0-flash

    choosing sides or teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ExecuteReader
    -0.54
    ConstraintMaker
    -0.52
     الرياضيه
    -0.51
    fitting
    -0.51
     JSTOR
    -0.50
    fit
    -0.49
    ometries
    -0.49
    Accomplished
    -0.48
    archiviato
    -0.48
    JsonKey
    -0.48
    POSITIVE LOGITS
     side
    1.46
     sides
    1.41
     sided
    1.17
    Side
    1.16
     Side
    1.16
     team
    1.14
    sides
    1.13
     SIDE
    1.10
    side
    1.10
     Team
    1.09
    Activations Density 0.388%

    No Known Activations