© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8487
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to visibility and sight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heaton
    -0.44
     XCTest
    -0.38
     pię
    -0.38
    ruptedException
    -0.36
    μως
    -0.36
     придется
    -0.36
    WebServlet
    -0.36
     overeen
    -0.35
     Besøkt
    -0.35
     planter
    -0.34
    POSITIVE LOGITS
    ici
    0.66
    Mach
    0.61
     Visibility
    0.60
    InjectAttribute
    0.59
    udes
    0.58
     visibility
    0.57
     mach
    0.54
    BeginContext
    0.54
     Mach
    0.54
    EndContext
    0.54
    Activations Density 0.576%

    No Known Activations