© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2408
    Prev
    Next
    INDEX
    Explanations

    words related to military actions and geopolitical conflicts

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

    alignment or support

    np_acts-logits-general · gemini-2.0-flash

    siding with or supporting others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Acrobat
    -0.48
    Datuak
    -0.40
     improvis
    -0.40
    torta
    -0.40
     ping
    -0.40
     EXCEL
    -0.40
    __(/*!
    -0.39
     SqlCommand
    -0.39
    дук
    -0.39
     Exper
    -0.38
    POSITIVE LOGITS
     support
    0.88
     allegiance
    0.81
     apoyo
    0.81
     loyal
    0.78
     soutien
    0.77
     loyalty
    0.76
     siding
    0.74
    支持
    0.73
     apoyar
    0.72
     apoio
    0.72
    Activations Density 0.988%

    No Known Activations