© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 9774
    Prev
    Next
    INDEX
    Explanations

    references to military vehicles or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessFile
    -0.48
    RegressionTest
    -0.44
    noční
    -0.42
     mennesker
    -0.41
     BoxDecoration
    -0.41
    Хьажоргаш
    -0.40
    KommentareTeilen
    -0.40
     OnInit
    -0.40
    ⤹
    -0.40
     člověk
    -0.39
    POSITIVE LOGITS
     prototype
    0.66
     prototypes
    0.63
     decommission
    0.63
     modernized
    0.61
     armament
    0.60
     fleet
    0.60
     equipped
    0.59
     operational
    0.59
     equipping
    0.58
     осна
    0.57
    Activations Density 0.426%

    No Known Activations