© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2661
    Prev
    Next
    INDEX
    Explanations

    programming keywords related to data structures and their modifiers

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

    `final` keyword

    np_acts-logits-general · gemini-2.0-flash

    public static final declarations

    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
    <bos>
    -0.55
     BIA
    -0.47
    AM
    -0.45
    webElementXpaths
    -0.45
    ಣ
    -0.43
    copy
    -0.43
     presup
    -0.43
    asio
    -0.42
    if
    -0.41
    tamide
    -0.41
    POSITIVE LOGITS
     ModelExpression
    0.79
     int
    0.77
    encodeWith
    0.76
    AutoScale
    0.65
    complexContent
    0.65
    enumi
    0.64
     resourceCulture
    0.63
    EDEFAULT
    0.63
    QMetaType
    0.63
    WriteBarrier
    0.61
    Activations Density 0.047%

    No Known Activations