© 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. 0-GEMMASCOPE-RES-16K
    6. 8701
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and features related to the layout of urban environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    رير
    -0.47
     négo
    -0.43
    ictus
    -0.42
    templateUrl
    -0.41
    elsa
    -0.41
     uzak
    -0.40
     ondes
    -0.40
    وروبا
    -0.40
    setContentType
    -0.40
    لكتر
    -0.40
    POSITIVE LOGITS
     snippetHide
    0.89
    KommentareTeilen
    0.85
    iecie
    0.82
     Савезне
    0.74
     '\\;'
    0.73
    UserScript
    0.72
     дописавши
    0.72
    thâu
    0.72
    ConstraintMaker
    0.72
    Tembelea
    0.70
    Activations Density 1.616%

    No Known Activations