© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 49539
    Prev
    Next
    INDEX
    Explanations

    verbs related to the process of analyzing or the act of analysis itself

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

    analyzing processes and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.82
     يتيمه
    -0.79
    StoryboardSegue
    -0.75
    DispatchToProps
    -0.72
    migrationBuilder
    -0.71
    ConstraintMaker
    -0.71
    ########.
    -0.70
     surla
    -0.69
     GoogleFonts
    -0.68
    HomeAsUpEnabled
    -0.68
    POSITIVE LOGITS
    Analyze
    0.94
     analyze
    0.93
     Analyze
    0.92
    analyze
    0.92
     analyzing
    0.83
    Analyzer
    0.80
     analyzed
    0.79
    Analyzing
    0.79
     analisar
    0.75
     analyzes
    0.75
    Activations Density 0.023%

    No Known Activations