© 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 - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 5627
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures and their manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.70
    iſen
    -0.64
    ſehen
    -0.61
     queſta
    -0.61
    ſchen
    -0.61
    ſelf
    -0.60
    contentLoaded
    -0.59
    #
    -0.59
     deleteById
    -0.59
     newOwner
    -0.58
    POSITIVE LOGITS
    новништво
    0.41
    舞
    0.35
    作
    0.33
     مواليد
    0.33
    Vaata
    0.33
    到
    0.32
     themselves
    0.32
     ranks
    0.31
    <0xA3>
    0.30
    Aiheesta
    0.30
    Activations Density 0.179%

    No Known Activations