Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 13117
    Prev
    Next
    INDEX
    Explanations

    references to file paths or filenames

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

    filepath. method

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    run
    -0.45
    play
    -0.45
    trains
    -0.43
    roll
    -0.42
    mask
    -0.41
     barley
    -0.40
    count
    -0.39
    try
    -0.39
     cows
    -0.38
    rule
    -0.38
    POSITIVE LOGITS
    filepath
    2.56
     filepath
    1.64
     filePath
    0.90
    FilePath
    0.85
    filePath
    0.77
    httphttps
    0.76
    /***/
    0.73
    fpath
    0.72
     AssemblyTitle
    0.72
    RegressionTest
    0.71
    Activations Density 0.000%

    No Known Activations