© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 1666
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "Every" and its variations, indicating a focus on frequency or universality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.38
     asla
    -0.38
    crollView
    -0.38
    Espèce
    -0.37
    Хьажоргаш
    -0.36
     estekak
    -0.35
     cualquiera
    -0.35
     otomatig
    -0.32
    şört
    -0.32
     Namely
    -0.31
    POSITIVE LOGITS
    every
    0.92
     eneste
    0.87
     conceivable
    0.87
     single
    0.87
     aspect
    0.82
     inch
    0.76
     every
    0.75
     poffible
    0.75
    Every
    0.74
    ones
    0.74
    Activations Density 0.098%

    No Known Activations