© 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. 2-GEMMASCOPE-RES-16K
    11. 4391
    Prev
    Next
    INDEX
    Explanations

    words related to sealing or sealing mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     przer
    -0.38
     Fische
    -0.36
     zarar
    -0.36
    velocityY
    -0.35
     Scherer
    -0.35
     screenWidth
    -0.34
    Traceback
    -0.34
    IUrlHelper
    -0.34
    regelen
    -0.33
    钱包
    -0.33
    POSITIVE LOGITS
     tf
    0.81
     quest
    0.74
    Quest
    0.72
     Quest
    0.72
    quest
    0.71
    tf
    0.68
     seal
    0.67
    ValueStyle
    0.62
     Normdatei
    0.62
     createState
    0.61
    Activations Density 0.235%

    No Known Activations