Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13958
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting elements and mathematical notations

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

    LaTeX math expressions

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math and display environments

    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
    TemporalType
    -0.70
    eramente
    -0.54
    quelize
    -0.52
     Seitz
    -0.52
    contentLoaded
    -0.52
    InitVars
    -0.52
     useAppContext
    -0.52
     ProtoMessage
    -0.51
     Shakspeare
    -0.50
    сторія
    -0.48
    POSITIVE LOGITS
     xmlns
    1.02
     display
    0.98
    math
    0.93
    display
    0.76
     Display
    0.73
    MathML
    0.71
    abestanden
    0.68
     متعلقه
    0.66
     DISPLAY
    0.65
    Display
    0.64
    Activations Density 0.093%

    No Known Activations