© 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. 4-GEMMASCOPE-RES-16K
    11. 11785
    Prev
    Next
    INDEX
    Explanations

    specific numerical data points or values in a structured format

    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
    berdayakan
    -0.91
     Normdatei
    -0.82
     nakalista
    -0.70
    ArrowToggle
    -0.65
     مشارکت‌کنندگان
    -0.61
    ########.
    -0.60
     kasarigan
    -0.59
    inginan
    -0.59
    oredCriteria
    -0.58
    KommentareTeilen
    -0.57
    POSITIVE LOGITS
    webElement
    0.51
    XmlType
    0.45
    /-/
    0.45
    ereur
    0.44
    ttemberg
    0.44
     amnesty
    0.43
    UrlResolution
    0.42
    isure
    0.41
    年には
    0.40
     per
    0.40
    Activations Density 0.926%

    No Known Activations