© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 16174
    Prev
    Next
    INDEX
    Explanations

    references to military personnel and their roles or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁢
    -0.65
     betweenstory
    -0.60
    Kariera
    -0.58
    [++
    -0.57
    írito
    -0.55
    GIVEREF
    -0.55
    ipedi
    -0.52
    nesty
    -0.51
     RequestMethod
    -0.51
    __()
    -0.50
    POSITIVE LOGITS
    ByPrimaryKey
    0.61
    //
    0.58
    <bos>
    0.56
    WebServlet
    0.53
    /**
    0.52
    urlpatterns
    0.52
    /*
    0.51
     Military
    0.51
    StackNavigator
    0.51
     rospy
    0.49
    Activations Density 0.282%

    No Known Activations