© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 3529
    Prev
    Next
    INDEX
    Explanations

    references to religious figures and teachings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementGuid
    -0.48
    WriteTagHelper
    -0.46
    ंदीखरीदारी
    -0.46
    AndEndTag
    -0.42
    exitRule
    -0.42
     StatefulWidget
    -0.40
    RegressionTest
    -0.39
    icon
    -0.39
    الحياه
    -0.39
     jura
    -0.39
    POSITIVE LOGITS
     preached
    0.46
    windowFixed
    0.45
    TemporalType
    0.44
     AssemblyVersion
    0.43
     AuthService
    0.41
     disambiguazione
    0.39
     चीज़ों
    0.38
     insuffisamment
    0.38
    OGND
    0.37
     препратки
    0.37
    Activations Density 0.205%

    No Known Activations