© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 8920
    Prev
    Next
    INDEX
    Explanations

    references to pronouns, particularly "it" and "them."

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

    token 'it' followed by punctuation

    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
    RegressionTest
    -0.78
     '\\;'
    -0.65
    windowFixed
    -0.61
    ьаж
    -0.57
    parsedMessage
    -0.52
     kaarangay
    -0.49
    AnimationsModule
    -0.47
    TintMode
    -0.47
    saraba
    -0.45
     Wikimedijinoj
    -0.45
    POSITIVE LOGITS
     Jahrgang
    0.42
    Contains
    0.42
     drauf
    0.41
     ου
    0.39
     irgend
    0.39
    offsetHeight
    0.39
    containing
    0.39
    ubehör
    0.38
    metz
    0.38
     zawier
    0.38
    Activations Density 0.018%

    No Known Activations