© 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. 16-GEMMASCOPE-RES-16K
    11. 4637
    Prev
    Next
    INDEX
    Explanations

    elements and their attributes in a structured data format, likely related to programming or software interfaces

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

    Code-related tokens, such as operators or handlers

    np_acts-logits-general · gemini-2.0-flash

    assignments and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlType
    -0.64
    Tikang
    -0.62
    hésite
    -0.61
     OnInit
    -0.60
    DeleteBehavior
    -0.60
    brities
    -0.58
    PRNewswire
    -0.58
    arrêter
    -0.54
     pubblici
    -0.54
    arrête
    -0.53
    POSITIVE LOGITS
     general
    0.58
    bių
    0.51
    Izvori
    0.51
    intValue
    0.50
     non
    0.50
     other
    0.48
    Referències
    0.48
    cella
    0.47
     برانيه
    0.46
     ProtoMessage
    0.45
    Activations Density 0.588%

    No Known Activations