© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 44655
    Prev
    Next
    INDEX
    Explanations

    negative assertions or denials

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

    no followed by exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.53
     avoient
    -0.51
    RegressionTest
    -0.50
     nowhere
    -0.49
     Italijanski
    -0.49
     quelcon
    -0.48
     EconPapers
    -0.48
    nobody
    -0.47
     nobody
    -0.42
     nadie
    -0.42
    POSITIVE LOGITS
     substitutions
    0.61
     exceptions
    0.59
     refunds
    0.59
     abbreviations
    0.54
     disbursements
    0.52
    setCellStyle
    0.50
    PickerController
    0.49
     changes
    0.47
     substitutes
    0.47
     exchanges
    0.46
    Activations Density 0.021%

    No Known Activations