© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5639
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, particularly exponents and subscripts

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

    Superscript ordinal numbers

    np_acts-logits-general · gemini-2.0-flash

    ordinal suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.97
    {}",
    -0.77
    AccessorTable
    -0.70
    writeField
    -0.65
    clés
    -0.64
    fromnode
    -0.63
    <()>
    -0.63
    WillAppear
    -0.61
    RectangleBorder
    -0.61
     ({
    -0.60
    POSITIVE LOGITS
    <em>
    0.73
    <sub>
    0.70
    <i>
    0.69
    <strong>
    0.66
    <u>
    0.64
    <code>
    0.61
    <b>
    0.60
    ​​​​
    0.55
    </sub>
    0.49
    <s>
    0.47
    Activations Density 0.268%

    No Known Activations