© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 12649
    Prev
    Next
    INDEX
    Explanations

    terms related to training, ideology, and discipline within a military or tactical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     medical
    -1.73
     doctors
    -1.68
     physicians
    -1.64
     Medical
    -1.61
     physician
    -1.60
     medically
    -1.56
    Medical
    -1.56
    Doctors
    -1.55
     doctor
    -1.54
    medical
    -1.54
    POSITIVE LOGITS
    SharedCtor
    0.50
     ujednoznacz
    0.46
    tanleria
    0.41
    oltà
    0.41
    beiter
    0.41
    bustible
    0.38
     Normdatei
    0.38
    izze
    0.37
     silt
    0.36
    stahl
    0.36
    Activations Density 1.927%

    No Known Activations