© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9506
    Prev
    Next
    INDEX
    Explanations

    code snippets pertaining to file and directory operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File system operations (directories/files)

    np_acts-logits-general · gemini-2.0-flash

    file system operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
    SpringRunner
    -0.41
    ConfigureAwait
    -0.41
     gustaría
    -0.40
     Erwartungen
    -0.40
     roligt
    -0.38
     Draht
    -0.36
     enää
    -0.35
     hanem
    -0.35
     inderdaad
    -0.35
     mukaan
    -0.35
    POSITIVE LOGITS
    listdir
    0.89
    makedirs
    0.84
    listFiles
    0.76
    existsSync
    0.74
    isfile
    0.71
     File
    0.66
    isDirectory
    0.64
    FileSystem
    0.63
     shutil
    0.62
    ioutil
    0.61
    Activations Density 0.213%

    No Known Activations