© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 1901
    Prev
    Next
    INDEX
    Explanations

    references to "position" or related terms in a context involving measurement or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.66
    Diweddarwch
    -0.54
    OGND
    -0.41
    ähkö
    -0.38
    RTLI
    -0.36
     Stras
    -0.36
     initComponents
    -0.35
    OleDb
    -0.35
     sklearn
    -0.34
    الحياه
    -0.33
    POSITIVE LOGITS
     position
    3.91
     Position
    3.66
    position
    3.52
    Position
    3.31
     POSITION
    3.28
     positions
    3.27
     Positions
    2.98
    POSITION
    2.91
     posición
    2.84
    positions
    2.73
    Activations Density 0.184%

    No Known Activations