© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5791
    Prev
    Next
    INDEX
    Explanations

    the word "near" and its variations in context, particularly regarding proximity or location

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

    "near"

    np_acts-logits-general · gemini-2.0-flash

    near a location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DialogContent
    -0.51
    ceptre
    -0.50
     getContent
    -0.49
     setContent
    -0.46
     setCode
    -0.45
     AssemblyVersion
    -0.45
     StringVar
    -0.45
     disp
    -0.44
     المعيارى
    -0.44
     AVL
    -0.44
    POSITIVE LOGITS
     near
    2.02
    near
    1.99
    Near
    1.94
     Near
    1.92
     NEAR
    1.63
    NEAR
    1.52
     nær
    1.09
     nears
    1.02
     dekat
    1.00
     près
    0.98
    Activations Density 0.085%

    No Known Activations