© 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. 9-GEMMASCOPE-RES-16K
    11. 7525
    Prev
    Next
    INDEX
    Explanations

    functions related to reading and writing data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataOutputStream
    -0.45
     competitiveness
    -0.43
    ENV
    -0.40
    ismet
    -0.39
    outputStream
    -0.38
     shooters
    -0.38
     gardes
    -0.37
     dispersion
    -0.36
    èdia
    -0.36
     RECOMEND
    -0.36
    POSITIVE LOGITS
     read
    0.82
    read
    0.75
    readValue
    0.73
     iprot
    0.72
     读取
    0.71
    readFile
    0.69
    Read
    0.67
    parsedMessage
    0.67
    ioutil
    0.67
    讀
    0.67
    Activations Density 0.494%

    No Known Activations