© 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. 14-GEMMASCOPE-RES-16K
    11. 9183
    Prev
    Next
    INDEX
    Explanations

    phrases indicating financial contributions or funding for educational or public initiatives

    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
     tiguan
    -0.51
    webElement
    -0.50
    帖最后由
    -0.48
    setopt
    -0.45
    endwhile
    -0.44
     saites
    -0.44
    AccessorTable
    -0.42
     nawr
    -0.42
    WithIOException
    -0.42
     BufferedReader
    -0.41
    POSITIVE LOGITS
     already
    0.48
     allerede
    0.48
    already
    0.48
    Уже
    0.44
     sejauh
    0.43
    -------
    0.41
    middels
    0.41
     bisher
    0.40
     Already
    0.40
     bereits
    0.39
    Activations Density 0.234%

    No Known Activations