© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15466
    Prev
    Next
    INDEX
    Explanations

    names and places, particularly related to geographical locations and individuals

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

    Welsh language and locations

    np_acts-logits-general · gemini-2.0-flash

    Welsh places and language

    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
    LookAnd
    -0.78
     Pease
    -0.71
    tableFuture
    -0.63
    NewUrlParser
    -0.62
     Shakspeare
    -0.61
     EconPapers
    -0.61
    Xna
    -0.58
    ConstraintMaker
    -0.58
     الرياضيه
    -0.57
     Danube
    -0.57
    POSITIVE LOGITS
     Welsh
    1.21
    Wales
    1.09
    Welsh
    1.08
     Wales
    1.08
     Cymru
    0.89
     Cardiff
    0.86
     wales
    0.79
    wales
    0.78
    Cardiff
    0.75
     Swansea
    0.69
    Activations Density 0.042%

    No Known Activations