© 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. 21-GEMMASCOPE-RES-16K
    11. 5778
    Prev
    Next
    INDEX
    Explanations

    statements and discussions related to governmental responsibilities and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.56
    HtmlAttribute
    -0.56
    BeginInit
    -0.50
    AddRange
    -0.49
    webElementGuid
    -0.49
     StringTokenizer
    -0.48
     Normdatei
    -0.48
    どうしても
    -0.47
    ableView
    -0.47
     doGet
    -0.47
    POSITIVE LOGITS
     demonstrates
    2.06
     demonstrating
    1.90
     proof
    1.89
     demonstrate
    1.89
     indicating
    1.87
     indicates
    1.86
     indicate
    1.81
     illustrates
    1.76
     dimost
    1.75
     demuestra
    1.72
    Activations Density 0.976%

    No Known Activations