© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2257
    Prev
    Next
    INDEX
    Explanations

    instances of the word "report" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onlyOwner
    -0.69
     Clay
    -0.65
    ethane
    -0.61
     թվական
    -0.61
     вра
    -0.59
     Ludwig
    -0.59
     javafx
    -0.58
    Alger
    -0.58
     Egy
    -0.57
    ANTAGES
    -0.57
    POSITIVE LOGITS
     report
    2.58
     reports
    2.49
    Report
    2.48
     Report
    2.46
     REPORT
    2.42
     Reports
    2.42
    report
    2.40
    Reports
    2.27
    reports
    2.26
    REPORT
    2.24
    Activations Density 0.084%

    No Known Activations