© 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. 34-GEMMASCOPE-RES-16K
    11. 6915
    Prev
    Next
    INDEX
    Explanations

    prefixes and roots associated with the word "und."

    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
     quedado
    -0.38
     ấm
    -0.38
    rungsseite
    -0.36
     Ergo
    -0.36
     Mete
    -0.34
     schuldig
    -0.33
    ANDUM
    -0.32
     caisse
    -0.31
     stället
    -0.31
     AutoMapper
    -0.30
    POSITIVE LOGITS
     мәкал
    0.70
    談社
    0.52
    addCriterion
    0.51
    enderror
    0.50
    abetes
    0.50
    Disc
    0.48
     CascadeType
    0.48
    dAtA
    0.47
    ;->
    0.46
    rawData
    0.45
    Activations Density 0.364%

    No Known Activations