© 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. 28-GEMMASCOPE-RES-16K
    11. 10611
    Prev
    Next
    INDEX
    Explanations

    structural elements in a HTML or XML-like markup language

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

    Code snippets or program-like text

    np_acts-logits-general · gemini-2.0-flash

    code comments and section breaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.02
     autorytatywna
    -0.93
     disambiguazione
    -0.90
     estekak
    -0.87
    الحياه
    -0.83
    SourceChecksum
    -0.83
    Personendaten
    -0.82
     препратки
    -0.81
    jsxFileName
    -0.80
    IsContent
    -0.79
    POSITIVE LOGITS
    <eos>
    0.49
    <h2>
    0.44
    ---
    0.42
    /*
    0.42
    Conclusion
    0.40
    let
    0.40
    <h3>
    0.39
    <u>
    0.39
    section
    0.39
    --
    0.39
    Activations Density 0.404%

    No Known Activations