© 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. 10-GEMMASCOPE-RES-16K
    6. 4075
    Prev
    Next
    INDEX
    Explanations

    phrases related to location or positioning within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.59
    brus
    -0.51
    времен
    -0.47
    yecek
    -0.47
     Bowden
    -0.46
     jiwa
    -0.45
     Lübeck
    -0.45
     Cardiff
    -0.44
     Comprometido
    -0.44
     regel
    -0.44
    POSITIVE LOGITS
     located
    1.26
     situated
    1.17
     berada
    1.04
     situe
    1.03
    located
    0.97
     positioned
    0.95
     Located
    0.94
     nestled
    0.94
     находится
    0.93
     nằm
    0.93
    Activations Density 0.343%

    No Known Activations