© 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. 5-GEMMASCOPE-RES-16K
    11. 9468
    Prev
    Next
    INDEX
    Explanations

    quotes and dialogue related to explaining actions, rules, and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     keterampilan
    -0.46
     d
    -0.43
     koordin
    -0.41
     dés
    -0.41
     genau
    -0.40
    wijl
    -0.40
     e
    -0.40
     chêne
    -0.40
     Indeed
    -0.39
    Indeed
    -0.39
    POSITIVE LOGITS
     typelib
    0.84
    脚注の使い方
    0.83
    RegressionTest
    0.75
    ंदीखरीदारी
    0.68
     ſever
    0.67
    tagHelperRunner
    0.67
     defaultstate
    0.67
     חיצוניים
    0.67
     oneself
    0.67
     NSCoder
    0.66
    Activations Density 0.250%

    No Known Activations