© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101894
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming language keywords and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indruk
    -0.36
     rather
    -0.33
    stdc
    -0.31
     accompanied
    -0.27
     perfectly
    -0.27
     fairly
    -0.25
     relatively
    -0.24
     strict
    -0.24
     lucht
    -0.23
     thus
    -0.23
    POSITIVE LOGITS
    TagMode
    0.91
     betweenstory
    0.84
    transQ
    0.75
    webElementGuid
    0.73
     transférez
    0.69
     authorisation
    0.65
    ंदीखरीदारी
    0.62
    piram
    0.62
    ImageContext
    0.61
    Portale
    0.61
    Activations Density 0.003%

    No Known Activations