© 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
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 11277
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "report" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.43
     CascadeType
    -0.41
     GenerationType
    -0.37
    uscular
    -0.37
     estekak
    -0.36
     MyClass
    -0.36
     Mast
    -0.35
    aaaaaa
    -0.35
     SX
    -0.35
     transformar
    -0.34
    POSITIVE LOGITS
     report
    4.03
    report
    3.63
     Report
    3.52
    Report
    3.45
     REPORT
    3.31
     reports
    3.14
    REPORT
    3.13
     Reports
    2.92
     reporting
    2.88
    reports
    2.83
    Activations Density 0.136%

    No Known Activations